# Gemini 4 ArgonHigh > Source: Benchize (https://benchize.com) — https://benchize.com/models/gemini-4-argon-high. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gemini-4-argon-high. Google Canonical URL: https://benchize.com/models/gemini-4-argon-high Last updated: Wed, 21 Oct 2026 18:05:10 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. Google ## Benchmarks | Benchmark | Score | ± | Rank | Cost | Latency | Source | | | --- | --- | --- | --- | --- | --- | --- | --- | | [Arena text style control / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts_english.md) | 1,551.35 | — | 1 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1551.348549740133 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1533.949203149005 rank 1 upper 1568.747896331261 variance 78.80788937976753 votes 1208 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 4 Argon (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3868/row` | | | | | | | | | [Arena text style control / instruction following](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ainstruction_following.md) | 1,525.35 | — | 1 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1525.3537595597604 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1510.7269592139812 rank 1 upper 1539.9805599055396 variance 55.69324007920196 votes 1748 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 4 Argon (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7534/row` | | | | | | | | | [Legal Research Bench / constitutional civil rights](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aconstitutional_civil_rights.md) | 47.37% | SE ±8.21 pp | 2 / 50 | $4.35 | 1,361.34source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 47.368 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.353414 \| USD \| per_test \| Lower is better \| \| `latency` \| 1361.337 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.21 pp sourcePopulation 82 stderr 8.209 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/constitutional_civil_rights/google~1gemini-4-argon` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate environmental esg](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__environmental_esg.md) | 97.31% | SE ±0.97 pp | 1 / 14 | $8.28 | 1,868.16source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 97.312 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 8.278315 \| USD \| per_test \| Lower is better \| \| `latency` \| 1868.158 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.97 pp sourcePopulation 24 stderr 0.97 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label google/gemini-4-argon Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__environmental_esg/google~1gemini-4-argon` | | | | | | | | | [Tax Agent Bench / weighted pass controversy precedence analysis](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Aweighted_pass__controversy_precedence_analysis.md) | 63.6% | SE ±8.39 pp | 12 / 46 | $4.08 | 1,204.53source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 63.603 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.081424 \| USD \| per_test \| Lower is better \| \| `latency` \| 1204.529 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.39 pp sourcePopulation 73 stderr 8.39 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/weighted_pass__controversy_precedence_analysis/google~1gemini-4-argon` | | | | | | | | | [Vibe Code Bench 1-100 / overall](https://benchize.com/benchmarks/vals-ai%3Avcb-1-100%3Aoverall.md) | 21.2% | SE ±3.81 pp | 7 / 16 | $18.66 | 6,179.48source duration | [Vals AI · 1.0](https://www.vals.ai/_astro/benchmark_view_vcb_1_100.ZqWqHxGl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 21.2 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 18.659304 \| USD \| per_test \| Lower is better \| \| `latency` \| 6179.48 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness OpenHands maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.81 pp sourcePopulation 25 stderr 3.811 tokenTotals {"cache_read_tokens":597101156,"cache_write_tokens":null,"input_tokens":750135416,"output_tokens":10070397,"reasoning_tokens":2747467} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vcb_1_100.ZqWqHxGl.json) Source Vals AI Original model label google/gemini-4-argon Source version 1.0 Observed 2026-10-21T16:46:09.131Z Evidence SHA-256 `4a3ebdcd9364ec3a21193d00de0bf723384d85187244abff859527fd3cc51891` Source locator `/tasks/overall/google~1gemini-4-argon` | | | | | | | | | [Arena text / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts.md) | 1,546 | — | 1 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1545.996369401194 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1535.1006535129964 rank 1 upper 1556.892085289392 variance 30.904047201234377 votes 3131 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 4 Argon (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3451/row` | | | | | | | | | [HLAB-Vals-1.1 / data privacy cybersecurity](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Adata_privacy_cybersecurity.md) | 50% | SE ±22.36 pp | 1 / 14 | $8.33 | 1,849.55source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 50 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 8.325019 \| USD \| per_test \| Lower is better \| \| `latency` \| 1849.552 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±22.36 pp sourcePopulation 24 stderr 22.361 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label google/gemini-4-argon Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/data_privacy_cybersecurity/google~1gemini-4-argon` | | | | | | | | | [EMB v1.1 / comps](https://benchize.com/benchmarks/vals-ai%3Aemb-v1-1%3Acomps.md) | 82.94% | SE ±3.44 pp | 1 / 19 | $11.77 | 2,301.06source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 82.94 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 11.770794 \| USD \| per_test \| Lower is better \| \| `latency` \| 2301.06 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.44 pp sourcePopulation 30 stderr 3.441 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label google/gemini-4-argon Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/comps/google~1gemini-4-argon` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / trusts estates private client](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Atrusts_estates_private_client.md) | 40% | SE ±24.5 pp | 1 / 49 | $16.18 | 3,234.1source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 40 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 16.183565 \| USD \| per_test \| Lower is better \| \| `latency` \| 3234.098 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±24.5 pp sourcePopulation 81 stderr 24.495 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/trusts_estates_private_client/google~1gemini-4-argon` | | | | | | | | | [Finance Agent (v2) / market analysis](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Amarket_analysis.md) | 79.71% | SE ±1.84 pp | 1 / 50 | $3.78 | 794.12source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 79.705 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.782093 \| USD \| per_test \| Lower is better \| \| `latency` \| 794.115 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.84 pp sourcePopulation 80 stderr 1.837 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label google/gemini-4-argon Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/market_analysis/google~1gemini-4-argon` | | | | | | | | | [CUA-bench / superhot](https://benchize.com/benchmarks/vals-ai%3Acua_bench%3Asuperhot.md) | 4% | SE ±0 pp | 6 / 8 | $50.11 | 103.85source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_cua_bench.DpgrKYWA.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 4 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 50.113634 \| USD \| per_test \| Lower is better \| \| `latency` \| 103.85 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort high harness antigravity maxOutputTokens 128000 provider google reasoning true Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 9 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_cua_bench.DpgrKYWA.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:46:16.228Z Evidence SHA-256 `8c415c63f28cd80496a4ccca27d1062ec98bb55268e58cba105b8cf2d7ee53d3` Source locator `/tasks/superhot/google~1gemini-4-argon` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / tax](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Atax.md) | 0% | SE ±0 pp | 3 / 49 | $10.88 | 2,790.46source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 10.875562 \| USD \| per_test \| Lower is better \| \| `latency` \| 2790.458 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 81 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/tax/google~1gemini-4-argon` | | | | | | | | | [CUA-bench / overall](https://benchize.com/benchmarks/vals-ai%3Acua_bench%3Aoverall.md) | 4.83% | SE ±0 pp | 7 / 8 | $193.78 | 70.51source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_cua_bench.DpgrKYWA.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 4.833333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 193.778921 \| USD \| per_test \| Lower is better \| \| `latency` \| 70.51 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort high harness antigravity maxOutputTokens 128000 provider google reasoning true Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 9 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_cua_bench.DpgrKYWA.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:46:16.228Z Evidence SHA-256 `8c415c63f28cd80496a4ccca27d1062ec98bb55268e58cba105b8cf2d7ee53d3` Source locator `/tasks/overall/google~1gemini-4-argon` | | | | | | | | | [EMB / overall](https://benchize.com/benchmarks/vals-ai%3Aemb%3Aoverall.md) | 75.24% | SE ±2.46 pp | 4 / 47 | $11.8 | 2,305.82source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 75.244 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 11.8029 \| USD \| per_test \| Lower is better \| \| `latency` \| 2305.821 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.46 pp sourcePopulation 76 stderr 2.459 tokenTotals {"cache_read_tokens":945025185,"cache_write_tokens":null,"input_tokens":1127460088,"output_tokens":14257556,"reasoning_tokens":9497334} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/overall/google~1gemini-4-argon` | | | | | | | | | [Code Migration v1.1 / code quality](https://benchize.com/benchmarks/vals-ai%3Acode-migration-v1-1%3Acode_quality.md) | 2.98% | SE ±0.05 pp | 13 / 17 | $44.79 | 8,528.47source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_code_migration_v1_1.bJHk6HEY.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 2.982 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 44.790194 \| USD \| per_test \| Lower is better \| \| `latency` \| 8528.468 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.05 pp sourcePopulation 26 stderr 0.051 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_code_migration_v1_1.bJHk6HEY.json) Source Vals AI Original model label google/gemini-4-argon Source version 1.1 Observed 2026-10-21T16:46:09.631Z Evidence SHA-256 `352faac603c73f05cc01e89214fb4adcafa05ea7432ea71ea9903a6b5fe36b08` Source locator `/tasks/code_quality/google~1gemini-4-argon` | | | | | | | | | [CyberBench v1.1 / patch](https://benchize.com/benchmarks/benchmark%3Acyber%3Apatch.md) | 85.71% | SE ±4.68 pp | 11 / 28 | $5 | 1,294.56source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_cyberbench.DS6UOlu0.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 85.714 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.998186 \| USD \| per_test \| Lower is better \| \| `latency` \| 1294.559 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.68 pp sourcePopulation 47 stderr 4.676 tokenTotals {"cache_read_tokens":370161604,"cache_write_tokens":null,"input_tokens":408936582,"output_tokens":2538309,"reasoning_tokens":2199322} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_cyberbench.DS6UOlu0.json) Source Vals AI Original model label google/gemini-4-argon Source version 1.1 Observed 2026-10-21T16:46:15.238Z Evidence SHA-256 `943f593f929f8971a6b746269a2851b5febc2aad4e2f1066895f715033cdc7f1` Source locator `/tasks/patch/google~1gemini-4-argon` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / intellectual property](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Aintellectual_property.md) | 20% | SE ±20 pp | 1 / 49 | $10.69 | 2,805.3source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 20 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 10.686247 \| USD \| per_test \| Lower is better \| \| `latency` \| 2805.298 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±20 pp sourcePopulation 81 stderr 20 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/intellectual_property/google~1gemini-4-argon` | | | | | | | | | [Earthborne Rangers (EBR-bench)](https://benchize.com/benchmarks/epoch-ai%3Aebr_bench.md) | 64.76% | SE ±4.9 pp | 3 / 13 | — | — | [epoch ai · EBR-bench](https://epoch.ai/data/benchmark_data.zip#file=ebr_bench.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.6476190476190476 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.6476190476190476 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion EBR-bench reasoningBudget Not reported Reasoning effort high sourceModelVersion gemini-4-argon_high ### Reported statistics Uncertainty Standard error: ±4.9 pp standardError 0.04902681019517619 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=ebr_bench.csv) Source epoch ai Original model label gemini-4-argon Source version EBR-bench Evaluated 2026-10-13T17:16:18.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `15ec96ff8e424623e6a7452956d849312f595f2b5cb4ebe70ec47831f9087b44` Source locator `/rows/0` | | | | | | | | | [Terminal-Bench 4.0 / overall](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-4%3Aoverall.md) | 57.58% | SE ±2.31 pp | 5 / 36 | $17.64 | 3,214.79source duration | [Vals AI · 4.0](https://www.vals.ai/_astro/benchmark_view_terminal_bench_4.CAnGyzC_.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 57.576 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 17.63994 \| USD \| per_test \| Lower is better \| \| `latency` \| 3214.793 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.31 pp sourcePopulation 52 stderr 2.314 tokenTotals {"cache_read_tokens":895783049,"cache_write_tokens":0,"input_tokens":1088824555,"output_tokens":10645668,"reasoning_tokens":6605548} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_4.CAnGyzC_.json) Source Vals AI Original model label google/gemini-4-argon Source version 4.0 Observed 2026-10-21T16:46:10.642Z Evidence SHA-256 `98f6964580e901f1aa143db664bd92aa558415f643569492545d67c47d7f519b` Source locator `/tasks/overall/google~1gemini-4-argon` | | | | | | | | | [Robo-bench / ninja course](https://benchize.com/benchmarks/vals-ai%3Arobo_bench%3Aninja_course.md) | 0% | SE ±0 pp | 1 / 5 | $0.99 | 180source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_robo_bench.DzDVSjnk.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.985995 \| USD \| per_test \| Lower is better \| \| `latency` \| 180 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort high harness antigravity maxOutputTokens Not reported provider google reasoning true Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 7 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_robo_bench.DzDVSjnk.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:46:05.362Z Evidence SHA-256 `79018880e0e64e5ee8ea196976a86b4ef42ed28e4ec2284db5d302d8aa6226a5` Source locator `/tasks/ninja_course/google~1gemini-4-argon` | | | | | | | | | [Robo-bench / balance scale](https://benchize.com/benchmarks/vals-ai%3Arobo_bench%3Abalance_scale.md) | 0% | SE ±0 pp | 4 / 5 | $0.52 | 145.52source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_robo_bench.DzDVSjnk.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.516261 \| USD \| per_test \| Lower is better \| \| `latency` \| 145.52 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort high harness antigravity maxOutputTokens Not reported provider google reasoning true Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 7 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_robo_bench.DzDVSjnk.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:46:05.362Z Evidence SHA-256 `79018880e0e64e5ee8ea196976a86b4ef42ed28e4ec2284db5d302d8aa6226a5` Source locator `/tasks/balance_scale/google~1gemini-4-argon` | | | | | | | | | [Terminal-Bench 4.0 / ml](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-4%3Aml.md) | 69.7% | SE ±3.03 pp | 4 / 36 | — | — | [Vals AI · 4.0](https://www.vals.ai/_astro/benchmark_view_terminal_bench_4.CAnGyzC_.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 69.697 \| percent \| reported \| Higher is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.03 pp sourcePopulation 52 stderr 3.03 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_4.CAnGyzC_.json) Source Vals AI Original model label google/gemini-4-argon Source version 4.0 Observed 2026-10-21T16:46:10.642Z Evidence SHA-256 `98f6964580e901f1aa143db664bd92aa558415f643569492545d67c47d7f519b` Source locator `/tasks/ml/google~1gemini-4-argon` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate data privacy cybersecurity](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__data_privacy_cybersecurity.md) | 97.53% | SE ±0.93 pp | 1 / 49 | $8.33 | 2,394.76source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 97.527 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 8.325019 \| USD \| per_test \| Lower is better \| \| `latency` \| 2394.758 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.93 pp sourcePopulation 81 stderr 0.925 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__data_privacy_cybersecurity/google~1gemini-4-argon` | | | | | | | | | [EMB v1.1 / overall](https://benchize.com/benchmarks/vals-ai%3Aemb-v1-1%3Aoverall.md) | 74.83% | SE ±2.49 pp | 4 / 19 | $11.8 | 2,305.82source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 74.828 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 11.8029 \| USD \| per_test \| Lower is better \| \| `latency` \| 2305.821 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.49 pp sourcePopulation 30 stderr 2.494 tokenTotals {"cache_read_tokens":945025185,"cache_write_tokens":null,"input_tokens":1127460088,"output_tokens":14257556,"reasoning_tokens":9497334} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label google/gemini-4-argon Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/overall/google~1gemini-4-argon` | | | | | | | | | [Arena text / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts_english.md) | 1,547.58 | — | 1 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1547.5797354104006 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1530.2936762767567 rank 1 upper 1564.865794544045 variance 77.78499115027637 votes 1208 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 4 Argon (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3868/row` | | | | | | | | | [Arena text / industry writing and literature and language](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_writing_and_literature_and_language.md) | 1,529.39 | — | 2 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1529.3893544358123 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1512.5545755356115 rank 2 upper 1546.2241333360128 variance 73.7766025479432 votes 1360 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 4 Argon (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7119/row` | | | | | | | | | [ProgramBench / strict](https://benchize.com/benchmarks/vals-ai%3Aprogrambench%3Astrict.md) | 2.5% | SE ±1.11 pp | 7 / 40 | $17.66 | 4,252.24source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_programbench.C_J7ZU4X.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 2.5 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 17.656424 \| USD \| per_test \| Lower is better \| \| `latency` \| 4252.235 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.11 pp sourcePopulation 64 stderr 1.107 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_programbench.C_J7ZU4X.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:46:10.137Z Evidence SHA-256 `e9bbb4378c7a058441a21d456baf9316b96c2cf5b58d371a3c7c803f5000bd8c` Source locator `/tasks/strict/google~1gemini-4-argon` | | | | | | | | | [LegalBench / rhetoric tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Arhetoric_tasks.md) | 82.84% | SE ±1.19 pp | 5 / 44 | $0.02 | 13.38source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 82.838 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.017171 \| USD \| per_test \| Lower is better \| \| `latency` \| 13.383 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.19 pp sourcePopulation 151 stderr 1.191 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:45:53.390Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/rhetoric_tasks/google~1gemini-4-argon` | | | | | | | | | [Arena text style control / industry life and physical and social science](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_life_and_physical_and_social_science.md) | 1,538.78 | — | 1 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1538.7756101366294 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1517.3431421349555 rank 1 upper 1560.208078138303 variance 119.57714662154521 votes 818 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 4 Argon (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5498/row` | | | | | | | | | [Short Story Writing — Pairwise Comparison](https://benchize.com/benchmarks/lechmazur-short-story%3Apairwise.md) | 0.8 | 95% CI 0.68–0.92 | 19 / 50 | — | — | [lechmazur short story · 8ba548d1cffefa5c472d3832e05f64e119a88fa4](https://api.github.com/repos/lechmazur/writing/contents/data/writing_gemini_argon_20261013/ratings.csv?ref=8ba548d1cffefa5c472d3832e05f64e119a88fa4) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `thurstone_rating` \| 0.7997952223558088 \| index \| pooled_observed_panel \| Higher is better \| \| `win_probability` \| 0.6188677077131939 \| score_fraction \| comparison_pool \| Higher is better \| ### Configuration benchmarkScope data/writing_gemini_argon_20261013 Reasoning effort high thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 0.68–0.92 bootstrapSamples 300 confidenceInterval95 ["0.6832085942797734","0.9176309890990524"] sourceRank 19 ### Source [Original source](https://api.github.com/repos/lechmazur/writing/contents/data/writing_gemini_argon_20261013/ratings.csv?ref=8ba548d1cffefa5c472d3832e05f64e119a88fa4) Source lechmazur short story Original model label Gemini 4 Argon (high) Source version 8ba548d1cffefa5c472d3832e05f64e119a88fa4 Observed 2026-10-21T16:34:21.130Z Evidence SHA-256 `c36baebed9f302ff7ad8fe97907d72e1757a015a39b6a3b23437597cf8e3bff6` Source locator `/rows/18` | | | | | | | | | [SAGE / overall](https://benchize.com/benchmarks/vals-ai%3Asage%3Aoverall.md) | 53.65% | SE ±3.39 pp | 4 / 41 | $0.1 | 63.07source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 53.645 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.097881 \| USD \| per_test \| Lower is better \| \| `latency` \| 63.068 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.39 pp sourcePopulation 91 stderr 3.385 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/overall/google~1gemini-4-argon` | | | | | | | | | [Tax Agent Bench / controversy precedence analysis](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Acontroversy_precedence_analysis.md) | 20% | SE ±7.43 pp | 5 / 46 | $4.08 | 1,204.53source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 20 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.081424 \| USD \| per_test \| Lower is better \| \| `latency` \| 1204.529 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±7.43 pp sourcePopulation 73 stderr 7.428 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/controversy_precedence_analysis/google~1gemini-4-argon` | | | | | | | | | [Code Migration / cobol](https://benchize.com/benchmarks/vals-ai%3Acode-migration%3Acobol.md) | 70% | SE ±15.28 pp | 1 / 47 | $10.58 | 2,563.51source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_code_migration.Dttzoqk3.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 70 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 10.578392 \| USD \| per_test \| Lower is better \| \| `latency` \| 2563.514 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±15.28 pp sourcePopulation 79 stderr 15.275 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_code_migration.Dttzoqk3.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:46:12.712Z Evidence SHA-256 `99194597f2c76c402195be47839409046e18bd30454616da6dd40b736a088fa4` Source locator `/tasks/cobol/google~1gemini-4-argon` | | | | | | | | | [SWE-bench Multimodal / highlight js](https://benchize.com/benchmarks/vals-ai%3Aswebench-multimodal%3Ahighlight_js.md) | 43.59% | SE ±8.04 pp | 4 / 14 | — | — | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 43.59 \| percent \| reported \| Higher is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.04 pp sourcePopulation 20 stderr 8.044 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:46:12.211Z Evidence SHA-256 `5302c42065b017d7deaa43d9e34be1ec69893b7ec4cceb6c07bfbabbd20b1f82` Source locator `/tasks/highlight_js/google~1gemini-4-argon` | | | | | | | | | [Finance Agent v2.1 / overall](https://benchize.com/benchmarks/vals-ai%3Afabv2-1%3Aoverall.md) | 67.66% | SE ±2 pp | 2 / 18 | $4.32 | 793.03source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 67.658 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.315759 \| USD \| per_test \| Lower is better \| \| `latency` \| 793.03 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2 pp sourcePopulation 28 stderr 2 tokenTotals {"cache_read_tokens":291037965,"cache_write_tokens":null,"input_tokens":602790494,"output_tokens":31627905,"reasoning_tokens":14149611} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) Source Vals AI Original model label google/gemini-4-argon Source version 2.1 Observed 2026-10-21T16:45:54.954Z Evidence SHA-256 `f1b0c2d7dca4e73b52136862a9be059f7c8481c69f15d705ce90bf3bd9f78429` Source locator `/tasks/overall/google~1gemini-4-argon` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate structured finance securitization](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__structured_finance_securitization.md) | 88.25% | SE ±1.82 pp | 4 / 49 | $13.41 | 3,445.55source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.254 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 13.409945 \| USD \| per_test \| Lower is better \| \| `latency` \| 3445.546 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.82 pp sourcePopulation 81 stderr 1.817 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__structured_finance_securitization/google~1gemini-4-argon` | | | | | | | | | [Vals Index / overall](https://benchize.com/benchmarks/vals-ai%3Avals_index%3Aoverall.md) | 69.24% | SE ±1.09 pp | 3 / 14 | $13.37 | 2,697.95source duration | [Vals AI · 2.2](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 69.237 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 13.372731 \| USD \| per_test \| Lower is better \| \| `latency` \| 2697.953 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.09 pp sourcePopulation 23 stderr 1.09 tokenTotals {"cache_read_tokens":12071919973,"cache_write_tokens":null,"input_tokens":13360828360,"output_tokens":146167290,"reasoning_tokens":59887853} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label google/gemini-4-argon Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/overall/google~1gemini-4-argon` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate antitrust competition](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__antitrust_competition.md) | 97.65% | SE ±0.91 pp | 1 / 14 | $15.54 | 1,611.73source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 97.645 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 15.535189 \| USD \| per_test \| Lower is better \| \| `latency` \| 1611.726 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.91 pp sourcePopulation 24 stderr 0.914 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label google/gemini-4-argon Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__antitrust_competition/google~1gemini-4-argon` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / environmental esg](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Aenvironmental_esg.md) | 0% | SE ±0 pp | 1 / 49 | $8.28 | 2,321.66source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 8.278315 \| USD \| per_test \| Lower is better \| \| `latency` \| 2321.664 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 81 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/environmental_esg/google~1gemini-4-argon` | | | | | | | | | [Vals Index / legal research](https://benchize.com/benchmarks/vals-ai%3Avals_index%3Alegal_research.md) | 54.81% | SE ±3.46 pp | 1 / 14 | $6.45 | 1,881.05source duration | [Vals AI · 2.2](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 54.808 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.44908 \| USD \| per_test \| Lower is better \| \| `latency` \| 1881.045 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.46 pp sourcePopulation 23 stderr 3.459 tokenTotals {"cache_read_tokens":739668768,"cache_write_tokens":0,"input_tokens":915877177,"output_tokens":24432059,"reasoning_tokens":11886477} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label google/gemini-4-argon Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/legal_research/google~1gemini-4-argon` | | | | | | | | | [HLAB-Vals-1.1 / international trade sanctions](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Ainternational_trade_sanctions.md) | 10% | SE ±10 pp | 3 / 14 | $7.01 | 1,409.55source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 10 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.007018 \| USD \| per_test \| Lower is better \| \| `latency` \| 1409.552 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±10 pp sourcePopulation 24 stderr 10 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label google/gemini-4-argon Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/international_trade_sanctions/google~1gemini-4-argon` | | | | | | | | | [Terminal-Bench-Science / physical sciences](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-science%3Aphysical_sciences.md) | 41.18% | SE ±12.3 pp | 4 / 30 | — | — | [Vals AI · 0.1](https://www.vals.ai/_astro/benchmark_view_terminal_bench_science.o-HR8Nyt.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 41.176 \| percent \| reported \| Higher is better \| ### Configuration computeEffort Not reported harness Mini-SWE-agent maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±12.3 pp sourcePopulation 41 stderr 12.304 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_science.o-HR8Nyt.json) Source Vals AI Original model label google/gemini-4-argon Source version 0.1 Observed 2026-10-21T16:46:03.529Z Evidence SHA-256 `a30a8618deaecf018ea1c8c9f675576cdd9ab79742d05788067db49afcc5f91b` Source locator `/tasks/physical_sciences/google~1gemini-4-argon` | | | | | | | | | [Tax Agent Bench / current temporal analysis](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Acurrent_temporal_analysis.md) | 66.67% | SE ±8.75 pp | 1 / 46 | $5.14 | 1,606.5source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 66.667 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.143482 \| USD \| per_test \| Lower is better \| \| `latency` \| 1606.495 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.75 pp sourcePopulation 73 stderr 8.754 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/current_temporal_analysis/google~1gemini-4-argon` | | | | | | | | | [Finance Agent v2.1 / all pass](https://benchize.com/benchmarks/vals-ai%3Afabv2-1%3Aall_pass.md) | 58.87% | SE ±2.17 pp | 1 / 18 | $4.32 | 793.03source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 58.868 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.315759 \| USD \| per_test \| Lower is better \| \| `latency` \| 793.03 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.17 pp sourcePopulation 28 stderr 2.168 tokenTotals {"cache_read_tokens":291037965,"cache_write_tokens":null,"input_tokens":602790494,"output_tokens":31627905,"reasoning_tokens":14149611} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) Source Vals AI Original model label google/gemini-4-argon Source version 2.1 Observed 2026-10-21T16:45:54.954Z Evidence SHA-256 `f1b0c2d7dca4e73b52136862a9be059f7c8481c69f15d705ce90bf3bd9f78429` Source locator `/tasks/all_pass/google~1gemini-4-argon` | | | | | | | | | [Arena text / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext%3Aexclude_ties.md) | 1,559.81 | — | 1 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1559.8103384223625 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1547.7171112240123 rank 1 upper 1571.9035656207127 variance 38.0704703335829 votes 3655 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 4 Argon (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2054/row` | | | | | | | | | [HLAB-Vals-1.1 / bankruptcy restructuring](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Abankruptcy_restructuring.md) | 0% | SE ±0 pp | 7 / 14 | $10.34 | 1,549.32source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 10.336011 \| USD \| per_test \| Lower is better \| \| `latency` \| 1549.322 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 24 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label google/gemini-4-argon Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/bankruptcy_restructuring/google~1gemini-4-argon` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / corporate governance](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acorporate_governance.md) | 20% | SE ±20 pp | 3 / 49 | $7.29 | 2,442.84source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 20 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.288851 \| USD \| per_test \| Lower is better \| \| `latency` \| 2442.838 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±20 pp sourcePopulation 81 stderr 20 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/corporate_governance/google~1gemini-4-argon` | | | | | | | | | [Arena text style control / chinese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Achinese.md) | 1,588.95 | — | 1 / 146 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1588.9542216369052 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1557.2786675418129 rank 1 upper 1620.6297757319976 variance 261.187422295425 votes 361 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 4 Argon (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/417/row` | | | | | | | | | [HLAB-Vals-1.1 / corporate governance](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acorporate_governance.md) | 60% | SE ±24.5 pp | 1 / 14 | $7.29 | 1,910.84source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 60 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.288851 \| USD \| per_test \| Lower is better \| \| `latency` \| 1910.844 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±24.5 pp sourcePopulation 24 stderr 24.495 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label google/gemini-4-argon Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/corporate_governance/google~1gemini-4-argon` | | | | | | | | | [HLAB-Vals-1.1 / corporate ma](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acorporate_ma.md) | 30% | SE ±20 pp | 2 / 14 | $8.13 | 1,717.44source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 30 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 8.132612 \| USD \| per_test \| Lower is better \| \| `latency` \| 1717.438 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±20 pp sourcePopulation 24 stderr 20 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label google/gemini-4-argon Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/corporate_ma/google~1gemini-4-argon` | | | | | | | | | [Mystery Game Puzzles](https://benchize.com/benchmarks/epoch-ai%3Amystery_game_puzzles.md) | 64% | SE ±4.82 pp | 5 / 71 | — | — | [epoch ai · Mystery Game Puzzles](https://epoch.ai/data/benchmark_data.zip#file=mystery_game_puzzles.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.64 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.64 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion Mystery Game Puzzles reasoningBudget Not reported Reasoning effort high sourceModelVersion gemini-4-argon_high ### Reported statistics Uncertainty Standard error: ±4.82 pp standardError 0.048241815132442176 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=mystery_game_puzzles.csv) Source epoch ai Original model label gemini-4-argon Source version Mystery Game Puzzles Evaluated 2026-10-13T17:14:57.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `795b977bc82c460a5e2c1d6dd7b2569ddb21853f3829c4f6fdd16edfaf47bfcf` Source locator `/rows/2` | | | | | | | | | [EMB v1.1 / dataroom](https://benchize.com/benchmarks/vals-ai%3Aemb-v1-1%3Adataroom.md) | 84.97% | SE ±4.56 pp | 11 / 19 | $7.11 | 1,426.81source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 84.974 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.109521 \| USD \| per_test \| Lower is better \| \| `latency` \| 1426.808 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.56 pp sourcePopulation 30 stderr 4.561 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label google/gemini-4-argon Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/dataroom/google~1gemini-4-argon` | | | | | | | | | [Vals Index / terminal bench 4](https://benchize.com/benchmarks/vals-ai%3Avals_index%3Aterminal_bench_4.md) | 57.58% | SE ±2.31 pp | 4 / 14 | $17.64 | 3,214.79source duration | [Vals AI · 2.2](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 57.576 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 17.63994 \| USD \| per_test \| Lower is better \| \| `latency` \| 3214.793 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.31 pp sourcePopulation 23 stderr 2.314 tokenTotals {"cache_read_tokens":895783049,"cache_write_tokens":0,"input_tokens":1088824555,"output_tokens":10645668,"reasoning_tokens":6605548} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label google/gemini-4-argon Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/terminal_bench_4/google~1gemini-4-argon` | | | | | | | | | [Arena text / non english](https://benchize.com/benchmarks/lmarena%3Atext%3Anon_english.md) | 1,521.53 | — | 1 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1521.5306575051807 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1510.4650375385818 rank 1 upper 1532.5962774717796 variance 31.875376246533534 votes 3000 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 4 Argon (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9731/row` | | | | | | | | | [Vals Index / finance agent](https://benchize.com/benchmarks/vals-ai%3Avals_index%3Afinance_agent.md) | 67.66% | SE ±2 pp | 2 / 14 | $4.32 | 793.03source duration | [Vals AI · 2.2](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 67.658 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.315759 \| USD \| per_test \| Lower is better \| \| `latency` \| 793.03 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2 pp sourcePopulation 23 stderr 2 tokenTotals {"cache_read_tokens":291037965,"cache_write_tokens":null,"input_tokens":602790494,"output_tokens":31627905,"reasoning_tokens":14149611} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label google/gemini-4-argon Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/finance_agent/google~1gemini-4-argon` | | | | | | | | | [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 98.5% | — | 1 / 213 | 0.16usd per task | — | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.985 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.16167408000000005 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup google-gemini-4-argon modelType CoT Reasoning effort high sourceModelVersion google-gemini-4-argon-high thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label Gemini 4 Argon (High) Source version v1 Observed 2026-10-21T16:34:20.378Z Evidence SHA-256 `302d8267c0522bf450ec1deeac4d060e2cf2fb444ba0a4269014d9535de0bd1f` Source locator `/evaluations/275` | | | | | | | | | [BullshitBench v2](https://benchize.com/benchmarks/bullshitbench%3Av2.md) | 65% | — | 33 / 191 | — | — | [bullshitbench · v2](https://api.github.com/repos/petergpt/bullshit-benchmark/contents/data/v2/latest/leaderboard.csv?ref=3c655234d15967738f95da696e3f938d4862dcf7) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `green_rate` \| 0.65 \| score_fraction \| all_attempts \| Higher is better \| \| `red_rate` \| 0.15 \| score_fraction \| all_attempts \| Lower is better \| \| `refusal_rate` \| 0.0 \| score_fraction \| all_attempts \| Lower is better \| \| `avg_score` \| 1.4867 \| score \| judge_grade_0_to_2 \| Higher is better \| ### Configuration Reasoning effort high suite v2 thinkingEnabled true ### Reported statistics acceptedCount 15 answeredCount 100 clearCount 65 errorCount 0 partialCount 20 rank 46 refusalCount 0 sampleSize 100 ### Source [Original source](https://api.github.com/repos/petergpt/bullshit-benchmark/contents/data/v2/latest/leaderboard.csv?ref=3c655234d15967738f95da696e3f938d4862dcf7) Source bullshitbench Original model label google/gemini-4-argon Source version v2 Observed 2026-10-21T16:33:56.675Z Evidence SHA-256 `98b485e08764d1c97144bc4f7b28ced1a96d50850947c775870dfda0e5d749b5` Source locator `/rows/45` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / international trade sanctions](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Ainternational_trade_sanctions.md) | 20% | SE ±20 pp | 1 / 49 | $7.01 | 2,018.01source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 20 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.007018 \| USD \| per_test \| Lower is better \| \| `latency` \| 2018.01 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±20 pp sourcePopulation 81 stderr 20 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/international_trade_sanctions/google~1gemini-4-argon` | | | | | | | | | [ProgramBench / almost](https://benchize.com/benchmarks/vals-ai%3Aprogrambench%3Aalmost.md) | 41% | SE ±3.49 pp | 7 / 40 | $17.66 | 4,252.24source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_programbench.C_J7ZU4X.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 41 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 17.656424 \| USD \| per_test \| Lower is better \| \| `latency` \| 4252.235 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.49 pp sourcePopulation 64 stderr 3.487 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_programbench.C_J7ZU4X.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:46:10.137Z Evidence SHA-256 `e9bbb4378c7a058441a21d456baf9316b96c2cf5b58d371a3c7c803f5000bd8c` Source locator `/tasks/almost/google~1gemini-4-argon` | | | | | | | | | [EMB / lbo](https://benchize.com/benchmarks/vals-ai%3Aemb%3Albo.md) | 68.54% | SE ±4.86 pp | 4 / 47 | $21.75 | 3,392.29source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 68.543 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 21.752123 \| USD \| per_test \| Lower is better \| \| `latency` \| 3392.293 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.86 pp sourcePopulation 76 stderr 4.858 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/google~1gemini-4-argon` | | | | | | | | | [IOI / ioi2024](https://benchize.com/benchmarks/vals-ai%3Aioi%3Aioi2024.md) | 100% | SE ±0 pp | 1 / 29 | $2.32 | 702.58source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 100 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.322254 \| USD \| per_test \| Lower is better \| \| `latency` \| 702.579 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 44 stderr 0 tokenTotals {"cache_read_tokens":5973062,"cache_write_tokens":0,"input_tokens":7390720,"output_tokens":353414,"reasoning_tokens":269441} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label google/gemini-4-argon Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2024/google~1gemini-4-argon` | | | | | | | | | [SWE-bench Multimodal / prism](https://benchize.com/benchmarks/vals-ai%3Aswebench-multimodal%3Aprism.md) | 63.16% | SE ±7.93 pp | 4 / 14 | — | — | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 63.158 \| percent \| reported \| Higher is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±7.93 pp sourcePopulation 20 stderr 7.93 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:46:12.211Z Evidence SHA-256 `5302c42065b017d7deaa43d9e34be1ec69893b7ec4cceb6c07bfbabbd20b1f82` Source locator `/tasks/prism/google~1gemini-4-argon` | | | | | | | | | [Arena text style control / industry entertainment and sports and media](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_entertainment_and_sports_and_media.md) | 1,518.57 | — | 1 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1518.5742456119654 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1500.4872480220445 rank 1 upper 1536.6612432018862 variance 85.16022091802384 votes 1235 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 4 Argon (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4693/row` | | | | | | | | | [Legal Research Bench / weighted pass constitutional civil rights](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aweighted_pass__constitutional_civil_rights.md) | 90.33% | SE ±2.29 pp | 1 / 50 | $4.35 | 1,361.34source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 90.334 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.353414 \| USD \| per_test \| Lower is better \| \| `latency` \| 1361.337 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.29 pp sourcePopulation 82 stderr 2.285 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/weighted_pass__constitutional_civil_rights/google~1gemini-4-argon` | | | | | | | | | [AudioMultiChallenge](https://benchize.com/benchmarks/scale%3Aaudiomc.md) | 58.41source score | CI 53.88–62.94 | 2 / 6 | — | — | [scale](https://labs.scale.com/leaderboard/audiomc) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 58.41 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort high Model configuration gemini-4-argon (high) sourceModelVersion Not reported thinkingEnabled true ### Reported statistics Uncertainty Confidence interval: 53.88–62.94 contaminationWarning Not reported rank 3 reportedConfidenceHalfWidth 4.53 ### Source [Original source](https://labs.scale.com/leaderboard/audiomc) Source scale Original model label gemini-4-argon (high) Observed 2026-10-21T16:35:33.690Z Evidence SHA-256 `1d659c306faff19bd29de2470af9e472df8aeaac8d655db5258a1e8679c090aa` Source locator `/rows/2` | | | | | | | | | [Finance Agent (v2) / financial modeling](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Afinancial_modeling.md) | 29.8% | SE ±1.82 pp | 6 / 50 | $3.87 | 923.89source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 29.803 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.869962 \| USD \| per_test \| Lower is better \| \| `latency` \| 923.889 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.82 pp sourcePopulation 80 stderr 1.815 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label google/gemini-4-argon Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/financial_modeling/google~1gemini-4-argon` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate corporate ma](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__corporate_ma.md) | 97.27% | SE ±0.93 pp | 2 / 14 | $8.13 | 1,717.44source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 97.267 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 8.132612 \| USD \| per_test \| Lower is better \| \| `latency` \| 1717.438 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.93 pp sourcePopulation 24 stderr 0.926 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label google/gemini-4-argon Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__corporate_ma/google~1gemini-4-argon` | | | | | | | | | [Public Benefits Bench v1.1 / overall](https://benchize.com/benchmarks/vals-ai%3Apublic-benefits-bench%3Aoverall.md) | 69.76% | SE ±0 pp | 6 / 34 | $2.79 | 1,566.79source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_snap.CUcEPb0v.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 69.756 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.793902 \| USD \| per_test \| Lower is better \| \| `latency` \| 1566.785 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 50 stderr 0 tokenTotals {"cache_read_tokens":559760847,"cache_write_tokens":null,"input_tokens":658538120,"output_tokens":6776808,"reasoning_tokens":3500703} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_snap.CUcEPb0v.json) Source Vals AI Original model label google/gemini-4-argon Source version 1.1 Observed 2026-10-21T16:46:17.865Z Evidence SHA-256 `6f091831ab607a26d65d2ade18cba7ce345ea3a67297b8c378e8a06ce398360d` Source locator `/tasks/overall/google~1gemini-4-argon` | | | | | | | | | [SWE-bench Multimodal / grommet](https://benchize.com/benchmarks/vals-ai%3Aswebench-multimodal%3Agrommet.md) | 45% | SE ±11.41 pp | 2 / 14 | — | — | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 45 \| percent \| reported \| Higher is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±11.41 pp sourcePopulation 20 stderr 11.413 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:46:12.211Z Evidence SHA-256 `5302c42065b017d7deaa43d9e34be1ec69893b7ec4cceb6c07bfbabbd20b1f82` Source locator `/tasks/grommet/google~1gemini-4-argon` | | | | | | | | | [Vals Science Index / terminal bench science](https://benchize.com/benchmarks/vals-ai%3Ascience_index%3Aterminal_bench_science.md) | 44.29% | SE ±5.98 pp | 5 / 17 | $44.9 | 6,369.1source duration | [Vals AI · 1.0](https://www.vals.ai/_astro/benchmark_view_science_index.CN7FN-f1.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 44.286 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 44.904641 \| USD \| per_test \| Lower is better \| \| `latency` \| 6369.095 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.98 pp sourcePopulation 21 stderr 5.98 tokenTotals {"cache_read_tokens":1635454933,"cache_write_tokens":0,"input_tokens":3866192418,"output_tokens":32152416,"reasoning_tokens":10397231} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_science_index.CN7FN-f1.json) Source Vals AI Original model label google/gemini-4-argon Source version 1.0 Observed 2026-10-21T16:45:50.879Z Evidence SHA-256 `fa4313008e91752fcfc185aaa78665f780d0fc23d7c7198a9853dbf2eaaaef1f` Source locator `/tasks/terminal_bench_science/google~1gemini-4-argon` | | | | | | | | | [Vals Index / vibe code bench](https://benchize.com/benchmarks/vals-ai%3Avals_index%3Avibe_code_bench.md) | 91.91% | SE ±1.9 pp | 2 / 14 | $8.11 | 2,247.68source duration | [Vals AI · 2.2](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 91.906 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 8.10797 \| USD \| per_test \| Lower is better \| \| `latency` \| 2247.675 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness OpenHands maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.9 pp sourcePopulation 23 stderr 1.899 tokenTotals {"cache_read_tokens":397575696,"cache_write_tokens":null,"input_tokens":451864686,"output_tokens":5436370,"reasoning_tokens":849287} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label google/gemini-4-argon Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/vibe_code_bench/google~1gemini-4-argon` | | | | | | | | | [Arena text style control / expert](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexpert.md) | 1,540.85 | — | 3 / 148 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1540.8534716061774 \| rating \| reported \| Higher is better \| ### Configuration category expert config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1514.558037646692 rank 3 upper 1567.1489055656627 variance 179.99668339350313 votes 507 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 4 Argon (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2473/row` | | | | | | | | | [Arena text / industry life and physical and social science](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_life_and_physical_and_social_science.md) | 1,547.91 | — | 1 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1547.9133461282813 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1526.797673050812 rank 1 upper 1569.0290192057507 variance 116.06831423328902 votes 818 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 4 Argon (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5498/row` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate insurance](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__insurance.md) | 96.32% | SE ±1.14 pp | 1 / 14 | $6.04 | 1,446.25source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 96.324 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.035978 \| USD \| per_test \| Lower is better \| \| `latency` \| 1446.246 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.14 pp sourcePopulation 24 stderr 1.143 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label google/gemini-4-argon Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__insurance/google~1gemini-4-argon` | | | | | | | | | [Arena text style control / creative writing](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acreative_writing.md) | 1,515.76 | — | 2 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1515.7612006968925 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1496.2680100570024 rank 2 upper 1535.2543913367826 variance 98.91671343087225 votes 1055 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 4 Argon (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1223/row` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / immigration](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Aimmigration.md) | 20% | SE ±20 pp | 2 / 49 | $9.27 | 2,775.57source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 20 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 9.272635 \| USD \| per_test \| Lower is better \| \| `latency` \| 2775.568 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±20 pp sourcePopulation 81 stderr 20 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/immigration/google~1gemini-4-argon` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / insurance](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Ainsurance.md) | 0% | SE ±0 pp | 2 / 49 | $6.04 | 1,949.21source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.035978 \| USD \| per_test \| Lower is better \| \| `latency` \| 1949.21 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 81 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/insurance/google~1gemini-4-argon` | | | | | | | | | [HLAB-Vals-1.1 / antitrust competition](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Aantitrust_competition.md) | 60% | SE ±24.5 pp | 1 / 14 | $15.54 | 1,611.73source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 60 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 15.535189 \| USD \| per_test \| Lower is better \| \| `latency` \| 1611.726 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±24.5 pp sourcePopulation 24 stderr 24.495 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label google/gemini-4-argon Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/antitrust_competition/google~1gemini-4-argon` | | | | | | | | | [SRE Bench / partial](https://benchize.com/benchmarks/vals-ai%3Asrebench%3Apartial.md) | 57.82% | SE ±2.88 pp | 3 / 24 | $30.45 | 5,695.71source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_sre_bench.Bd0uBJxH.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 57.824 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 30.451343 \| USD \| per_test \| Lower is better \| \| `latency` \| 5695.712 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.88 pp sourcePopulation 35 stderr 2.878 tokenTotals {"cache_read_tokens":17516454239,"cache_write_tokens":null,"input_tokens":18511814639,"output_tokens":43486854,"reasoning_tokens":28271875} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sre_bench.Bd0uBJxH.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:46:15.724Z Evidence SHA-256 `a10b2c964f5878b0fc21c888703f311a5ef7d7a74fc3c529cab3ddd9fa474e2b` Source locator `/tasks/partial/google~1gemini-4-argon` | | | | | | | | | [EMB / operating](https://benchize.com/benchmarks/vals-ai%3Aemb%3Aoperating.md) | 69.43% | SE ±5.48 pp | 11 / 47 | $10.71 | 2,370.25source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 69.433 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 10.710486 \| USD \| per_test \| Lower is better \| \| `latency` \| 2370.247 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.48 pp sourcePopulation 76 stderr 5.478 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/operating/google~1gemini-4-argon` | | | | | | | | | [Finance Agent v2.1 / market analysis](https://benchize.com/benchmarks/vals-ai%3Afabv2-1%3Amarket_analysis.md) | 70.67% | SE ±6.62 pp | 2 / 18 | $3.2 | 550.7source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 70.673 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.201461 \| USD \| per_test \| Lower is better \| \| `latency` \| 550.697 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.62 pp sourcePopulation 28 stderr 6.617 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) Source Vals AI Original model label google/gemini-4-argon Source version 2.1 Observed 2026-10-21T16:45:54.954Z Evidence SHA-256 `f1b0c2d7dca4e73b52136862a9be059f7c8481c69f15d705ce90bf3bd9f78429` Source locator `/tasks/market_analysis/google~1gemini-4-argon` | | | | | | | | | [Tax Agent Bench / fact pattern analysis](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Afact_pattern_analysis.md) | 39.54% | SE ±7.54 pp | 6 / 46 | $2.85 | 812.52source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 39.535 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.8502 \| USD \| per_test \| Lower is better \| \| `latency` \| 812.519 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±7.54 pp sourcePopulation 73 stderr 7.544 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/fact_pattern_analysis/google~1gemini-4-argon` | | | | | | | | | [EMB v1.1 / template](https://benchize.com/benchmarks/vals-ai%3Aemb-v1-1%3Atemplate.md) | 79.55% | SE ±2.89 pp | 4 / 19 | $16.14 | 2,452.6source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 79.553 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 16.142633 \| USD \| per_test \| Lower is better \| \| `latency` \| 2452.597 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.89 pp sourcePopulation 30 stderr 2.887 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label google/gemini-4-argon Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/template/google~1gemini-4-argon` | | | | | | | | | [Finance Agent v2.1 / comparables](https://benchize.com/benchmarks/vals-ai%3Afabv2-1%3Acomparables.md) | 61.73% | SE ±6.46 pp | 1 / 18 | $5.81 | 963.32source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 61.733 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.814253 \| USD \| per_test \| Lower is better \| \| `latency` \| 963.322 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.46 pp sourcePopulation 28 stderr 6.462 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) Source Vals AI Original model label google/gemini-4-argon Source version 2.1 Observed 2026-10-21T16:45:54.954Z Evidence SHA-256 `f1b0c2d7dca4e73b52136862a9be059f7c8481c69f15d705ce90bf3bd9f78429` Source locator `/tasks/comparables/google~1gemini-4-argon` | | | | | | | | | [Tax Agent Bench / numbers calculations](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Anumbers_calculations.md) | 60% | SE ±9.1 pp | 2 / 46 | $1.95 | 526.54source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 60 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.946484 \| USD \| per_test \| Lower is better \| \| `latency` \| 526.541 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±9.1 pp sourcePopulation 73 stderr 9.097 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/numbers_calculations/google~1gemini-4-argon` | | | | | | | | | [Vals Science Index / biomysterybench](https://benchize.com/benchmarks/vals-ai%3Ascience_index%3Abiomysterybench.md) | 76.3% | SE ±0.37 pp | 6 / 17 | $5.71 | 2,396.82source duration | [Vals AI · 1.0](https://www.vals.ai/_astro/benchmark_view_science_index.CN7FN-f1.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 76.296 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.707134 \| USD \| per_test \| Lower is better \| \| `latency` \| 2396.816 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.37 pp sourcePopulation 21 stderr 0.37 tokenTotals {"cache_read_tokens":149000710,"cache_write_tokens":0,"input_tokens":187578219,"output_tokens":16476596,"reasoning_tokens":11274521} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_science_index.CN7FN-f1.json) Source Vals AI Original model label google/gemini-4-argon Source version 1.0 Observed 2026-10-21T16:45:50.879Z Evidence SHA-256 `fa4313008e91752fcfc185aaa78665f780d0fc23d7c7198a9853dbf2eaaaef1f` Source locator `/tasks/biomysterybench/google~1gemini-4-argon` | | | | | | | | | [IOI / overall](https://benchize.com/benchmarks/vals-ai%3Aioi%3Aoverall.md) | 100% | SE ±0 pp | 1 / 29 | $5.31 | 1,459.27source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 100 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.307626 \| USD \| per_test \| Lower is better \| \| `latency` \| 1459.27 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 44 stderr 0 tokenTotals {"cache_read_tokens":46123808,"cache_write_tokens":0,"input_tokens":48678879,"output_tokens":620036,"reasoning_tokens":445230} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label google/gemini-4-argon Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/overall/google~1gemini-4-argon` | | | | | | | | | [Arena text style control / russian](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Arussian.md) | 1,525.63 | — | 2 / 150 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1525.6303243005823 \| rating \| reported \| Higher is better \| ### Configuration category russian config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1502.757024560383 rank 2 upper 1548.5036240407821 variance 136.19509291276958 votes 668 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 4 Argon (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10385/row` | | | | | | | | | [AutomationBench](https://benchize.com/benchmarks/zapier%3Aautomationbench.md) | 51.29% | — | 1 / 113 | $1.7 | — | [zapier](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 51.29 \| percent \| reported \| Higher is better \| \| `cost` \| 1.7 \| USD \| per_task \| Lower is better \| ### Configuration benchmarkVersion 1.0.6 costFootnote true Fallback policy Not reported Reasoning effort high Model configuration Gemini 4 Argon (High) thinkingEnabled true ### Reported statistics rank 1 ### Source [Original source](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) Source zapier Original model label Gemini 4 Argon (High) Observed 2026-10-21T16:34:56.783Z Evidence SHA-256 `43978e38f018789fa59c11de5328abe9e5905bfa9a5a4d601fa3aa4d9c153b0d` Source locator `/rows/0` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate employment labor](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__employment_labor.md) | 88.76% | SE ±1.94 pp | 3 / 49 | $6.39 | 2,165.54source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.764 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.38748 \| USD \| per_test \| Lower is better \| \| `latency` \| 2165.544 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.94 pp sourcePopulation 81 stderr 1.936 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__employment_labor/google~1gemini-4-argon` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate healthcare life sciences](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__healthcare_life_sciences.md) | 97.82% | SE ±0.85 pp | 1 / 14 | $8.84 | 2,163.43source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 97.819 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 8.843854 \| USD \| per_test \| Lower is better \| \| `latency` \| 2163.428 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.85 pp sourcePopulation 24 stderr 0.848 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label google/gemini-4-argon Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__healthcare_life_sciences/google~1gemini-4-argon` | | | | | | | | | [HLAB-Vals-1.1 / white collar defense investigations](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Awhite_collar_defense_investigations.md) | 0% | SE ±0 pp | 2 / 14 | $10.94 | 1,880.17source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 10.940583 \| USD \| per_test \| Lower is better \| \| `latency` \| 1880.166 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 24 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label google/gemini-4-argon Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/white_collar_defense_investigations/google~1gemini-4-argon` | | | | | | | | | [Arena text style control / overall](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aoverall.md) | 1,523.93 | — | 1 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1523.9263411254742 \| rating \| reported \| Higher is better \| ### Configuration category overall config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1515.1028237474814 rank 1 upper 1532.749858503467 variance 20.26689925721342 votes 4900 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 4 Argon (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/0/row` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate international trade sanctions](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__international_trade_sanctions.md) | 96.22% | SE ±1.21 pp | 2 / 14 | $7.01 | 1,409.55source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 96.215 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.007018 \| USD \| per_test \| Lower is better \| \| `latency` \| 1409.552 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.21 pp sourcePopulation 24 stderr 1.207 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label google/gemini-4-argon Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/google~1gemini-4-argon` | | | | | | | | | [HLAB-Vals-1.1 / overall](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Aoverall.md) | 27.08% | SE ±3.74 pp | 1 / 14 | $10.55 | 1,755.4source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 27.083 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 10.54836 \| USD \| per_test \| Lower is better \| \| `latency` \| 1755.397 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.74 pp sourcePopulation 24 stderr 3.738 tokenTotals {"cache_read_tokens":733823568,"cache_write_tokens":null,"input_tokens":812145091,"output_tokens":18424207,"reasoning_tokens":5211457} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label google/gemini-4-argon Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/overall/google~1gemini-4-argon` | | | | | | | | | [Arena text / instruction following](https://benchize.com/benchmarks/lmarena%3Atext%3Ainstruction_following.md) | 1,533.92 | — | 2 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1533.9231390434584 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1519.3696194204122 rank 2 upper 1548.4766586665046 variance 55.13658828708246 votes 1748 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 4 Argon (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7535/row` | | | | | | | | | [Finance Agent (v2) / adjustments](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Aadjustments.md) | 60.53% | SE ±2.14 pp | 1 / 50 | $4.2 | 911.57source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 60.527 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.200264 \| USD \| per_test \| Lower is better \| \| `latency` \| 911.574 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.14 pp sourcePopulation 80 stderr 2.143 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label google/gemini-4-argon Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/adjustments/google~1gemini-4-argon` | | | | | | | | | [Arena text style control / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_business_and_management_and_financial_operations.md) | 1,520.77 | — | 1 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1520.774541748575 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1500.3482045250405 rank 1 upper 1541.2008789721096 variance 108.61375114107304 votes 890 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 4 Argon (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4283/row` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / litigation dispute resolution](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Alitigation_dispute_resolution.md) | 0% | SE ±0 pp | 6 / 49 | $10.29 | 2,932.17source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 10.28651 \| USD \| per_test \| Lower is better \| \| `latency` \| 2932.168 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 81 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/litigation_dispute_resolution/google~1gemini-4-argon` | | | | | | | | [Next page](https://benchize.com/models/gemini-4-argon-high.md?cursor=4c271599291ffebdef7a903cf0330f63a873070f630d0863a9ae7d74a2318989) --- Cite as: Gemini 4 ArgonHigh — Benchize, https://benchize.com/models/gemini-4-argon-high (retrieved 2026-10-21)