# Gemini 4 Argon

> Source: Benchize (https://benchize.com) — https://benchize.com/models/gemini-4-argon. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gemini-4-argon.

Google

Canonical URL: https://benchize.com/models/gemini-4-argon
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 | Source |  |
| --- | --- | --- | --- | --- | --- | --- |
| [Rapidata SVG generation — Alignment](https://benchize.com/benchmarks/rapidata%3Asvg%3Arlb_1MFkk9yZHssERh.md) | 1,665.63elo | CI 1,628.62–1,702.64 | 1 / 37 | — | [rapidata · v1](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkk9yZHssERh) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1665.6280411041453 \| elo \| rlb_1MFkk9yZHssERh \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkk9yZHssERh participantId par_1Xsgz12KP2Vun0 sourceModelVersion gemini-4-argon weighted false ### Reported statistics Uncertainty Confidence interval: 1,628.62–1,702.64 confidenceIntervalLowerOffset 37.00814268637487 confidenceIntervalUpperOffset 37.00814268637487 totalMatches 3295 wins 2706 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkk9yZHssERh) Source rapidata Original model label gemini-4-argon Source version v1 Observed 2026-10-21T16:37:40.342Z Evidence SHA-256 `2f5c8d08728735790b500d930d71b66f04253f1209f7c1c3da0db0846c163fcf` Source locator `/items/0` |  |  |  |  |  |  |
| [HiL-Bench (Human-in-Loop Benchmark)](https://benchize.com/benchmarks/scale%3Ahil.md) | 62source score | CI 56.69–67.31 | 3 / 22 | — | [scale](https://labs.scale.com/leaderboard/hil) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 62 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Gemini 4 Argon sourceModelVersion gemini-4-argon thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 56.69–67.31 contaminationWarning Not reported rank 5 reportedConfidenceHalfWidth 5.31 ### Source [Original source](https://labs.scale.com/leaderboard/hil) Source scale Original model label Gemini 4 Argon Observed 2026-10-21T16:35:30.082Z Evidence SHA-256 `043a333e27453edada150667c7f4439b2aab463f37928c2153c6aa79f33dd1b2` Source locator `/rows/4` |  |  |  |  |  |  |
| [FrontierSWE v2 abs](https://benchize.com/benchmarks/frontierswe%3Av2%3Aabs.md) | 54.96source score | — | 4 / 15 | — | [frontierswe](https://www.frontierswe.com/) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `overall` \| 54.96118588235292 \| source_score \| mean \| Higher is better \| \| `overall_best` \| 64.30448529411764 \| source_score \| best \| Higher is better \| \| `overall_worst` \| 44.45035882352941 \| source_score \| worst \| Higher is better \| \| `implementation` \| 74.46000428571429 \| source_score \| mean \| Higher is better \| \| `performance` \| 35.03570666666667 \| source_score \| mean \| Higher is better \| \| `research` \| 47.668540952380944 \| source_score \| mean \| Higher is better \| ### Configuration aggregation mean harness proximus normalization abs Reasoning effort unknown ### Source [Original source](https://www.frontierswe.com/) Source frontierswe Original model label Gemini 4 Argon Observed 2026-10-21T16:31:27.602Z Evidence SHA-256 `818e027068cf61ff1aadd8281b6e49e9c6795221015210601b5e34d0d223e5b5` Source locator `/rows/3` |  |  |  |  |  |  |
| [ArXivLean 09/2026](https://benchize.com/benchmarks/matharena%3Aarxivlean--september.md) | 39.62% | 95% CI 26.45–52.79% | 2 / 6 | 40.39usd per problem | [matharena · arxivlean--september](https://matharena.ai/competition_tables/arxivlean--september) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 39.62 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 40.39 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxivlean--september predicted false sourceModelName Gemini 4 Argon sourceModelVersion gemini/gemini-4-argon ### Reported statistics Uncertainty 95% confidence interval: 26.45–52.79% confidenceInterval95 13.17 problems 53 ### Source [Original source](https://matharena.ai/competition_tables/arxivlean--september) Source matharena Original model label Gemini 4 Argon Source version arxivlean--september Observed 2026-10-21T16:52:22.825Z Evidence SHA-256 `5d42ba0bbc37cc684861959960e17e45edb8cd93395dfe74b44e3252f043c42d` Source locator `/table/rows/1` |  |  |  |  |  |  |
| [Rapidata Text-to-3D with LLM code — Overall preference](https://benchize.com/benchmarks/rapidata%3Atext-to-3d-code%3Aoverall.md) | 1,605.59elo | CI 1,589.32–1,621.86 | 1 / 9 | — | [rapidata](https://api.rapidata.ai/benchmark/bmk_1YVpXgN69Mv8I9/standings/query) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1605.5891218218403 \| elo \| overall \| Higher is better \| ### Configuration benchmarkId bmk_1YVpXgN69Mv8I9 criterion overall participantId par_1YVpXvedTGpH53 sourceModelVersion gemini-4-argon weighted false ### Reported statistics Uncertainty Confidence interval: 1,589.32–1,621.86 confidenceIntervalLowerOffset 16.266400046822355 confidenceIntervalUpperOffset 16.266400046822582 totalMatches 15664.571376892109 wins 12512.464249481915 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1YVpXgN69Mv8I9/standings/query) Source rapidata Original model label gemini-4-argon Source version Observed 2026-10-21T16:37:41.757Z Evidence SHA-256 `048d6dec5a711f63fb70b09a6495cf440b0bf6f34f80156b97832c611e7a2913` Source locator `/items/0` |  |  |  |  |  |  |
| [PRBench Finance](https://benchize.com/benchmarks/scale%3Aprbench-finance.md) | 49.9source score | CI 49.48–50.32 | 8 / 22 | — | [scale](https://labs.scale.com/leaderboard/prbench-finance) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 49.9 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Gemini 4 Argon sourceModelVersion gemini/gemini-4-argon thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 49.48–50.32 contaminationWarning Not reported rank 11 reportedConfidenceHalfWidth 0.42 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-finance) Source scale Original model label Gemini 4 Argon Observed 2026-10-21T16:35:34.798Z Evidence SHA-256 `948d67409f0ae9c93fd41428f634cfc93c7815a21f43690cecb9095c9d3ec8f1` Source locator `/rows/10` |  |  |  |  |  |  |
| [Rapidata Text-to-3D with LLM code — Preference](https://benchize.com/benchmarks/rapidata%3Atext-to-3d-code%3Arlb_1YVpXugYHlm63x.md) | 1,794.09elo | CI 1,755.84–1,832.33 | 1 / 9 | — | [rapidata](https://api.rapidata.ai/benchmark/bmk_1YVpXgN69Mv8I9/standings/query?leaderboard_id%5Beq%5D=rlb_1YVpXugYHlm63x) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1794.0870915055439 \| elo \| rlb_1YVpXugYHlm63x \| Higher is better \| ### Configuration benchmarkId bmk_1YVpXgN69Mv8I9 criterion rlb_1YVpXugYHlm63x participantId par_1YVpXvedTGpH53 sourceModelVersion gemini-4-argon weighted false ### Reported statistics Uncertainty Confidence interval: 1,755.84–1,832.33 confidenceIntervalLowerOffset 38.24402134101956 confidenceIntervalUpperOffset 38.24402134101956 totalMatches 3614 wins 3061 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1YVpXgN69Mv8I9/standings/query?leaderboard_id%5Beq%5D=rlb_1YVpXugYHlm63x) Source rapidata Original model label gemini-4-argon Source version Observed 2026-10-21T16:37:43.410Z Evidence SHA-256 `a30cb5e42eb353cd3fadbb4c6519873ad22d3f0528a4e569fbbe40160928d934` Source locator `/items/0` |  |  |  |  |  |  |
| [Vending-Bench 2](https://benchize.com/benchmarks/vendingbench%3Av2.md) | — | — | — | $13,718.16 | [vendingbench](https://andonlabs.com/_app/immutable/chunks/Cjn0_qj9.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `final_balance` \| 13718.158333333333 \| USD \| one_simulated_year \| Higher is better \| \| `geometric_mean_balance` \| 11726.45551442005 \| USD \| positive_final_balances \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Gemini 4 Argon thinkingEnabled Not reported ### Reported statistics confidenceHalfWidth95 6076.023182318204 positiveBalanceRuns 6 runCount 6 standardDeviation 7593.4471744904295 standardError 3100.0118277133693 ### Source [Original source](https://andonlabs.com/_app/immutable/chunks/Cjn0_qj9.js) Source vendingbench Original model label Gemini 4 Argon Observed 2026-10-21T16:36:40.592Z Evidence SHA-256 `1a0b043147050298c405bcb743d73e425d532464202231cd18c27f836fa5f223` Source locator `/rows/46` |  |  |  |  |  |  |
| [BrokenArXiv 08/2026](https://benchize.com/benchmarks/matharena%3Aarxiv_false--august.md) | 54.17% | 95% CI 41.12–67.22% | 10 / 11 | 8.9usd per problem | [matharena · arxiv_false--august](https://matharena.ai/competition_tables/arxiv_false--august) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 54.17 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 8.90 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv_false--august predicted false sourceModelName Gemini 4 Argon sourceModelVersion gemini/gemini-4-argon ### Reported statistics Uncertainty 95% confidence interval: 41.12–67.22% confidenceInterval95 13.05 problems 56 ### Source [Original source](https://matharena.ai/competition_tables/arxiv_false--august) Source matharena Original model label Gemini 4 Argon Source version arxiv_false--august Observed 2026-10-21T16:52:25.683Z Evidence SHA-256 `1facf024f36359a3fcf069fc3b747d7fbf6aeec67c7949ed674b50ec0447a209` Source locator `/table/rows/10` |  |  |  |  |  |  |
| [Rapidata Text-to-3D with LLM code — Creativity](https://benchize.com/benchmarks/rapidata%3Atext-to-3d-code%3Arlb_1YVqTDVUylKrUp.md) | 1,841.61elo | CI 1,807.27–1,875.94 | 1 / 9 | — | [rapidata](https://api.rapidata.ai/benchmark/bmk_1YVpXgN69Mv8I9/standings/query?leaderboard_id%5Beq%5D=rlb_1YVqTDVUylKrUp) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1841.6091816404892 \| elo \| rlb_1YVqTDVUylKrUp \| Higher is better \| ### Configuration benchmarkId bmk_1YVpXgN69Mv8I9 criterion rlb_1YVqTDVUylKrUp participantId par_1YVpXvedTGpH53 sourceModelVersion gemini-4-argon weighted false ### Reported statistics Uncertainty Confidence interval: 1,807.27–1,875.94 confidenceIntervalLowerOffset 34.334584647377596 confidenceIntervalUpperOffset 34.334584647377824 totalMatches 4823 wins 4261 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1YVpXgN69Mv8I9/standings/query?leaderboard_id%5Beq%5D=rlb_1YVqTDVUylKrUp) Source rapidata Original model label gemini-4-argon Source version Observed 2026-10-21T16:37:42.177Z Evidence SHA-256 `4ce251bc655221de3fef117b85e05f775323a39098049de2bbfd4835ca2c6293` Source locator `/items/0` |  |  |  |  |  |  |
| [DesignArena Overall frontend coding](https://benchize.com/benchmarks/designarena%3Acode.md) | 1,329elo | SE ±3.63 | 11 / 116 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=code) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1329 \| elo \| code \| Higher is better \| ### Configuration arenaType models category allcategories inputModality text sourceModelVersion gemini-4-argon variationName public ### Reported statistics Uncertainty Standard error: ±3.63 averageGenerationTimeMs 229080 battles 10440 losses 4421 standardError 3.6262 winRate 57.6 wins 6019 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=code) Source designarena Original model label Gemini 4 Argon Source version public Observed 2026-10-21T16:37:57.301Z Evidence SHA-256 `0c897b58670f5e352bd123db999a40c0d1781a443964c502b90774a76a3a7758` Source locator `/data/12` |  |  |  |  |  |  |
| [DesignArena Image to web application](https://benchize.com/benchmarks/designarena%3Aimage-to-webapp.md) | 1,317elo | SE ±20.88 | 1 / 24 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=image-to-webapp) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1317 \| elo \| image-to-webapp \| Higher is better \| ### Configuration arenaType agents category agon_webapps inputModality image sourceModelVersion gemini-4-argon variationName public ### Reported statistics Uncertainty Standard error: ±20.88 averageGenerationTimeMs Not reported battles 317 losses 123 standardError 20.877 winRate 61.2 wins 194 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=image-to-webapp) Source designarena Original model label Gemini 4 Argon Source version public Observed 2026-10-21T16:37:59.412Z Evidence SHA-256 `cc4e49fc057d3b786184ff44b697422e2420a174e8a98a80a77aa65021921ab4` Source locator `/data/0` |  |  |  |  |  |  |
| [DesignArena UI component generation](https://benchize.com/benchmarks/designarena%3Aui-components.md) | 1,330elo | — | 12 / 112 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ui-components) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1330 \| elo \| ui-components \| Higher is better \| ### Configuration arenaType models category uicomponent inputModality Not reported sourceModelVersion gemini-4-argon variationName public ### Reported statistics averageGenerationTimeMs 147310 battles 549 losses 232 standardError Not reported winRate 57.7 wins 317 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ui-components) Source designarena Original model label Gemini 4 Argon Source version public Observed 2026-10-21T16:37:57.993Z Evidence SHA-256 `46482ec1b4012638eace65493daea4750e2088098018fd9d5fc46126fc1f8557` Source locator `/data/13` |  |  |  |  |  |  |
| [ArXivMath 09/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--september.md) | 87.74% | 95% CI 81.5–93.98% | 2 / 6 | 3.24usd per problem | [matharena · arxiv--september](https://matharena.ai/competition_tables/arxiv--september) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 87.74 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 3.24 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--september predicted false sourceModelName Gemini 4 Argon sourceModelVersion gemini/gemini-4-argon ### Reported statistics Uncertainty 95% confidence interval: 81.5–93.98% confidenceInterval95 6.24 problems 53 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--september) Source matharena Original model label Gemini 4 Argon Source version arxiv--september Observed 2026-10-21T16:52:30.640Z Evidence SHA-256 `8973b7bb8ea675057eb4c03cedc79d40de49d0a1b15da24d387eaaad2d82b3be` Source locator `/table/rows/1` |  |  |  |  |  |  |
| [Rapidata SVG generation — Overall preference](https://benchize.com/benchmarks/rapidata%3Asvg%3Aoverall.md) | 1,319.55elo | CI 1,301.84–1,337.27 | 5 / 37 | — | [rapidata · v1](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1319.5529184402876 \| elo \| overall \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion overall participantId par_1Xsgz12KP2Vun0 sourceModelVersion gemini-4-argon weighted false ### Reported statistics Uncertainty Confidence interval: 1,301.84–1,337.27 confidenceIntervalLowerOffset 17.716742939821188 confidenceIntervalUpperOffset 17.716742939821188 totalMatches 9885.325140721507 wins 6719.285586546297 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query) Source rapidata Original model label gemini-4-argon Source version v1 Observed 2026-10-21T16:37:39.078Z Evidence SHA-256 `4b73ff7e4ca0ecfd64f7888c2d64f3398a058c945c4644acd54eddb330e16d66` Source locator `/items/7` |  |  |  |  |  |  |
| [Rapidata SVG generation — Coherence](https://benchize.com/benchmarks/rapidata%3Asvg%3Arlb_1MFkkBzpuU8fTG.md) | 778.06elo | CI 749.35–806.76 | 35 / 37 | — | [rapidata · v1](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkBzpuU8fTG) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 778.0561314718566 \| elo \| rlb_1MFkkBzpuU8fTG \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkBzpuU8fTG participantId par_1Xsgz12KP2Vun0 sourceModelVersion gemini-4-argon weighted false ### Reported statistics Uncertainty Confidence interval: 749.35–806.76 confidenceIntervalLowerOffset 28.70796142947063 confidenceIntervalUpperOffset 28.707961429470515 totalMatches 3295 wins 1213 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkBzpuU8fTG) Source rapidata Original model label gemini-4-argon Source version v1 Observed 2026-10-21T16:37:39.715Z Evidence SHA-256 `aa3cb94ff16f544c58adeea35b9087d281c785058b8ce1ae0f98a7ff84920930` Source locator `/items/62` |  |  |  |  |  |  |
| [DesignArena Data visualization generation](https://benchize.com/benchmarks/designarena%3Adata-viz.md) | 1,336elo | — | 5 / 99 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=data-viz) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1336 \| elo \| data-viz \| Higher is better \| ### Configuration arenaType models category dataviz inputModality Not reported sourceModelVersion gemini-4-argon variationName public ### Reported statistics averageGenerationTimeMs 181297 battles 292 losses 114 standardError Not reported winRate 61 wins 178 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=data-viz) Source designarena Original model label Gemini 4 Argon Source version public Observed 2026-10-21T16:37:58.264Z Evidence SHA-256 `a895f6f1a25fa8eb01f821c2097ddec4f884de7bd22f1b8a22e82e6679b71849` Source locator `/data/6` |  |  |  |  |  |  |
| [DesignArena Image to HTML](https://benchize.com/benchmarks/designarena%3Aimage-to-html.md) | 1,270elo | — | 2 / 35 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=image-to-html) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1270 \| elo \| image-to-html \| Higher is better \| ### Configuration arenaType models category website inputModality image sourceModelVersion gemini-4-argon variationName public ### Reported statistics averageGenerationTimeMs 227162 battles 1042 losses 416 standardError Not reported winRate 60.1 wins 626 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=image-to-html) Source designarena Original model label Gemini 4 Argon Source version public Observed 2026-10-21T16:37:58.959Z Evidence SHA-256 `94f97ebbdd53a8c56f138b620e59b3a9b35c66c3954dcaaa1b2ed4c71518b404` Source locator `/data/1` |  |  |  |  |  |  |
| [PRBench Legal](https://benchize.com/benchmarks/scale%3Aprbench-legal.md) | 49.41source score | CI 49.04–49.78 | 9 / 26 | — | [scale](https://labs.scale.com/leaderboard/prbench-legal) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 49.41 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Gemini 4 Argon sourceModelVersion gemini/gemini-4-argon thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 49.04–49.78 contaminationWarning Not reported rank 12 reportedConfidenceHalfWidth 0.37 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label Gemini 4 Argon Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/11` |  |  |  |  |  |  |
| [Rapidata Text-to-3D with LLM code — Alignment](https://benchize.com/benchmarks/rapidata%3Atext-to-3d-code%3Arlb_1YVpXug2nDeUlV.md) | 1,576.04elo | CI 1,542.84–1,609.23 | 2 / 9 | — | [rapidata](https://api.rapidata.ai/benchmark/bmk_1YVpXgN69Mv8I9/standings/query?leaderboard_id%5Beq%5D=rlb_1YVpXug2nDeUlV) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1576.036405778354 \| elo \| rlb_1YVpXug2nDeUlV \| Higher is better \| ### Configuration benchmarkId bmk_1YVpXgN69Mv8I9 criterion rlb_1YVpXug2nDeUlV participantId par_1YVpXvedTGpH53 sourceModelVersion gemini-4-argon weighted false ### Reported statistics Uncertainty Confidence interval: 1,542.84–1,609.23 confidenceIntervalLowerOffset 33.19681294893235 confidenceIntervalUpperOffset 33.19681294893235 totalMatches 3614 wins 2834 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1YVpXgN69Mv8I9/standings/query?leaderboard_id%5Beq%5D=rlb_1YVpXug2nDeUlV) Source rapidata Original model label gemini-4-argon Source version Observed 2026-10-21T16:37:42.991Z Evidence SHA-256 `a2223beea99910879fd4c5ded70604d3d62dcff1f04a3b617d13f28f03a75948` Source locator `/items/1` |  |  |  |  |  |  |
| [ArXivMath 08/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--august.md) | 82.46% | 95% CI 72.59–92.33% | 7 / 11 | 4.61usd per problem | [matharena · arxiv--august](https://matharena.ai/competition_tables/arxiv--august) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 82.46 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 4.61 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--august predicted false sourceModelName Gemini 4 Argon sourceModelVersion gemini/gemini-4-argon ### Reported statistics Uncertainty 95% confidence interval: 72.59–92.33% confidenceInterval95 9.87 problems 57 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--august) Source matharena Original model label Gemini 4 Argon Source version arxiv--august Observed 2026-10-21T16:52:30.283Z Evidence SHA-256 `5924e5ecc15ff087ec1504b1e4ac44408b005c4f70e81e0d2184f930383a963c` Source locator `/table/rows/6` |  |  |  |  |  |  |
| [BrokenArXiv 09/2026](https://benchize.com/benchmarks/matharena%3Aarxiv_false--september.md) | 49.69% | 95% CI 40.13–59.25% | 4 / 6 | 7.22usd per problem | [matharena · arxiv_false--september](https://matharena.ai/competition_tables/arxiv_false--september) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 49.69 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 7.22 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv_false--september predicted false sourceModelName Gemini 4 Argon sourceModelVersion gemini/gemini-4-argon ### Reported statistics Uncertainty 95% confidence interval: 40.13–59.25% confidenceInterval95 9.56 problems 53 ### Source [Original source](https://matharena.ai/competition_tables/arxiv_false--september) Source matharena Original model label Gemini 4 Argon Source version arxiv_false--september Observed 2026-10-21T16:52:26.084Z Evidence SHA-256 `4431a852d035438c3451a917deda38fbe7f7e38a2da0903d97e836c3b8776de1` Source locator `/table/rows/3` |  |  |  |  |  |  |
| [DesignArena Browser game generation](https://benchize.com/benchmarks/designarena%3Agame-dev.md) | 1,376elo | — | 8 / 117 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=game-dev) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1376 \| elo \| game-dev \| Higher is better \| ### Configuration arenaType models category gamedev inputModality Not reported sourceModelVersion gemini-4-argon variationName public ### Reported statistics averageGenerationTimeMs 215249 battles 1276 losses 471 standardError Not reported winRate 63.1 wins 805 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=game-dev) Source designarena Original model label Gemini 4 Argon Source version public Observed 2026-10-21T16:38:01.100Z Evidence SHA-256 `53db6a89112ce8cdf644568c666d4b8309aece764cfcedb291ffd52ae3934e30` Source locator `/data/7` |  |  |  |  |  |  |
| [DesignArena Website generation](https://benchize.com/benchmarks/designarena%3Awebsite.md) | 1,315elo | — | 10 / 123 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=website) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1315 \| elo \| website \| Higher is better \| ### Configuration arenaType models category website inputModality text sourceModelVersion gemini-4-argon variationName public ### Reported statistics averageGenerationTimeMs 246858 battles 7779 losses 3402 standardError Not reported winRate 56.3 wins 4377 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=website) Source designarena Original model label Gemini 4 Argon Source version public Observed 2026-10-21T16:37:57.757Z Evidence SHA-256 `51873e97776a3c5ae706b24cc2c60384793dd18398df970e213a8e7c276d8ac0` Source locator `/data/11` |  |  |  |  |  |  |
| [Humanity's Last Exam (Diamond)](https://benchize.com/benchmarks/scale%3Ahle-diamond.md) | 53.2source score | CI 50.13–56.27 | 3 / 12 | — | [scale](https://labs.scale.com/leaderboard/hle-diamond) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 53.2 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration gemini-4-argon sourceModelVersion gemini-4-argon thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 50.13–56.27 contaminationWarning Not reported rank 3 reportedConfidenceHalfWidth 3.07 ### Source [Original source](https://labs.scale.com/leaderboard/hle-diamond) Source scale Original model label gemini-4-argon Observed 2026-10-21T16:35:27.820Z Evidence SHA-256 `c60d42f5aacdf787d9ccc8b70817766d86707776a7f8b44ef0337cb9ae60bf20` Source locator `/rows/2` |  |  |  |  |  |  |
| [Rapidata Text-to-3D with LLM code — Coherence](https://benchize.com/benchmarks/rapidata%3Atext-to-3d-code%3Arlb_1YVpXufudyOLlc.md) | 1,271.85elo | CI 1,242.84–1,300.85 | 5 / 9 | — | [rapidata](https://api.rapidata.ai/benchmark/bmk_1YVpXgN69Mv8I9/standings/query?leaderboard_id%5Beq%5D=rlb_1YVpXufudyOLlc) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1271.8450182222773 \| elo \| rlb_1YVpXufudyOLlc \| Higher is better \| ### Configuration benchmarkId bmk_1YVpXgN69Mv8I9 criterion rlb_1YVpXufudyOLlc participantId par_1YVpXvedTGpH53 sourceModelVersion gemini-4-argon weighted false ### Reported statistics Uncertainty Confidence interval: 1,242.84–1,300.85 confidenceIntervalLowerOffset 29.0070039258635 confidenceIntervalUpperOffset 29.007003925863728 totalMatches 3614 wins 2357 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1YVpXgN69Mv8I9/standings/query?leaderboard_id%5Beq%5D=rlb_1YVpXufudyOLlc) Source rapidata Original model label gemini-4-argon Source version Observed 2026-10-21T16:37:42.585Z Evidence SHA-256 `59243752590bb5f22389edbe87b8cc11b00e9a6fc49b5b94753544fc8780e58d` Source locator `/items/4` |  |  |  |  |  |  |
| [DesignArena 3D design generation](https://benchize.com/benchmarks/designarena%3A3d-design.md) | 1,389elo | — | 8 / 110 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=3d-design) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1389 \| elo \| 3d-design \| Higher is better \| ### Configuration arenaType models category 3d inputModality Not reported sourceModelVersion gemini-4-argon variationName public ### Reported statistics averageGenerationTimeMs 146977 battles 1083 losses 382 standardError Not reported winRate 64.7 wins 701 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=3d-design) Source designarena Original model label Gemini 4 Argon Source version public Observed 2026-10-21T16:37:58.515Z Evidence SHA-256 `bcc0267f7bc7e9ec112306b3a35413cf78bbccbfaa838356232d5d5ed0b83d0f` Source locator `/data/8` |  |  |  |  |  |  |
| [Rapidata SVG generation — Preference](https://benchize.com/benchmarks/rapidata%3Asvg%3Arlb_1MFkkEMFnCNyKl.md) | 1,753.02elo | CI 1,713.65–1,792.4 | 1 / 37 | — | [rapidata · v1](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1753.0223472511775 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1Xsgz12KP2Vun0 sourceModelVersion gemini-4-argon weighted false ### Reported statistics Uncertainty Confidence interval: 1,713.65–1,792.4 confidenceIntervalLowerOffset 39.37650392076739 confidenceIntervalUpperOffset 39.37650392076739 totalMatches 3295 wins 2793 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label gemini-4-argon Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/0` |  |  |  |  |  |  |

---
Cite as: Gemini 4 Argon — Benchize, https://benchize.com/models/gemini-4-argon (retrieved 2026-10-21)