# EMB v1.1 / scratch > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/vals-ai%3Aemb-v1-1%3Ascratch. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/vals-ai%3Aemb-v1-1%3Ascratch. Evaluating agents on Excel-based financial modeling tasks, graded by the GPT-6 Luna rubric judge with template scoring fixes Canonical URL: https://benchize.com/benchmarks/vals-ai%3Aemb-v1-1%3Ascratch Last updated: Wed, 21 Oct 2026 18:52:20 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. Evaluating agents on Excel-based financial modeling tasks, graded by the GPT-6 Luna rubric judge with template scoring fixes Professional work · Models tested: 19 · Score publishers: Vals AI ## Model results | # | Model | Score | ± | Cost | Latency | | | --- | --- | --- | --- | --- | --- | --- | | 1 | [Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max | 72.67% | SE ±2.41 pp | $15.31 | 1,843.68source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 72.674 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 15.305899 \| USD \| per_test \| Lower is better \| \| `latency` \| 1843.681 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.41 pp sourcePopulation 30 stderr 2.405 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label anthropic/claude-fable-5-1 Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/scratch/anthropic~1claude-fable-5-1` | | | | | | | | 2 | [GPT-6 Astra](https://benchize.com/models/gpt-6-astra-max.md)Max | 70.87% | SE ±2.54 pp | $5.89 | 887.07source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 70.865 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.886751 \| USD \| per_test \| Lower is better \| \| `latency` \| 887.067 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.54 pp sourcePopulation 30 stderr 2.54 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/scratch/openai~1gpt-6-astra` | | | | | | | | 3 | [Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-max.md)Max | 70.82% | SE ±3.15 pp | $8.58 | 2,251.75source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 70.815 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 8.575324 \| USD \| per_test \| Lower is better \| \| `latency` \| 2251.753 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.15 pp sourcePopulation 30 stderr 3.153 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label anthropic/claude-sonnet-5-5 Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/scratch/anthropic~1claude-sonnet-5-5` | | | | | | | | 4 | [Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-max.md)Max | 70.25% | SE ±3.17 pp | $11.27 | 2,284.4source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 70.249 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 11.266649 \| USD \| per_test \| Lower is better \| \| `latency` \| 2284.395 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.17 pp sourcePopulation 30 stderr 3.169 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/scratch/anthropic~1claude-opus-5-5` | | | | | | | | 5 | [Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High | 70% | SE ±2.69 pp | $7.46 | 2,159.05source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 69.999 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.463166 \| USD \| per_test \| Lower is better \| \| `latency` \| 2159.046 \| 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: ±2.69 pp sourcePopulation 30 stderr 2.693 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/scratch/google~1gemini-4-argon` | | | | | | | | 6 | [Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max | 68.85% | SE ±2.72 pp | $3.79 | 949.84source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 68.848 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.785539 \| USD \| per_test \| Lower is better \| \| `latency` \| 949.838 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 131072 provider Meta reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.72 pp sourcePopulation 30 stderr 2.723 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label meta/muse-wonder Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/scratch/meta~1muse-wonder` | | | | | | | | 7 | [Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High | 68.54% | SE ±2.79 pp | $6.98 | 724.8source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 68.544 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.984969 \| USD \| per_test \| Lower is better \| \| `latency` \| 724.799 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.79 pp sourcePopulation 30 stderr 2.792 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-3.8-flash Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/scratch/google~1gemini-3.8-flash` | | | | | | | | 8 | [GPT-6 Luna](https://benchize.com/models/gpt-6-luna-max.md)Max | 68.13% | SE ±2.49 pp | $0.11 | 996.44source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 68.125 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.108806 \| USD \| per_test \| Lower is better \| \| `latency` \| 996.439 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.49 pp sourcePopulation 30 stderr 2.488 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label openai/gpt-6-luna Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/scratch/openai~1gpt-6-luna` | | | | | | | | 9 | [DeepSeek V4.1 Flash 1017](https://benchize.com/models/deepseek-v4-1-flash-1017-max.md)Max | 67.33% | SE ±2.64 pp | $0.32 | 2,030.02source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 67.325 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.315566 \| USD \| per_test \| Lower is better \| \| `latency` \| 2030.015 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature 1 topP 1 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.64 pp sourcePopulation 30 stderr 2.64 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label deepseek/deepseek-v4.1-flash-1017 Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/scratch/deepseek~1deepseek-v4.1-flash-1017` | | | | | | | | 10 | [GPT-6.1 Sol](https://benchize.com/models/gpt-6-1-sol-max.md)Max | 66.94% | SE ±3.43 pp | $1.29 | 1,255.71source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 66.937 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.290012 \| USD \| per_test \| Lower is better \| \| `latency` \| 1255.708 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.43 pp sourcePopulation 30 stderr 3.427 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label openai/gpt-6.1-sol Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/scratch/openai~1gpt-6.1-sol` | | | | | | | | 11 | [Step 5 Preview](https://benchize.com/models/step-5-preview.md) | 66.57% | SE ±2.53 pp | $1.22 | 2,506.87source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 66.568 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.217876 \| USD \| per_test \| Lower is better \| \| `latency` \| 2506.874 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 1024000 provider Stepfun reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.53 pp sourcePopulation 30 stderr 2.529 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label stepfun/step-5-preview Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/scratch/stepfun~1step-5-preview` | | | | | | | | 12 | [MiMo-V2.6-Flash](https://benchize.com/models/mimo-v2-6-flash.md) | 65.68% | SE ±2.48 pp | $0.1 | 1,471.5source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 65.681 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.10021 \| USD \| per_test \| Lower is better \| \| `latency` \| 1471.499 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Xiaomi reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.48 pp sourcePopulation 30 stderr 2.482 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label xiaomi/mimo-v2.6-flash Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/scratch/xiaomi~1mimo-v2.6-flash` | | | | | | | | 13 | [DeepSeek V4 Pro 0813](https://benchize.com/models/deepseek-v4-pro-0813-max.md)Max | 65.43% | SE ±2.55 pp | $1.05 | 2,260.45source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 65.433 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.045429 \| USD \| per_test \| Lower is better \| \| `latency` \| 2260.453 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.55 pp sourcePopulation 30 stderr 2.548 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/scratch/deepseek~1deepseek-v4-pro-0813` | | | | | | | | 14 | [DeepSeek V4.1 Flash](https://benchize.com/models/deepseek-v4-1-flash-max.md)Max | 65.24% | SE ±2.74 pp | $0.21 | 714.92source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 65.238 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.211272 \| USD \| per_test \| Lower is better \| \| `latency` \| 714.918 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature 1 topP 1 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.74 pp sourcePopulation 30 stderr 2.741 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label deepseek/deepseek-v4.1-flash Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/scratch/deepseek~1deepseek-v4.1-flash` | | | | | | | | 15 | [MiniMax M3.1 Flash](https://benchize.com/models/minimax-m3-1-flash-max.md)Max | 63.89% | SE ±2.41 pp | $0.24 | 1,822.61source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 63.888 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.242112 \| USD \| per_test \| Lower is better \| \| `latency` \| 1822.607 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 262144 provider MiniMax reasoning Not reported Reasoning effort max Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.41 pp sourcePopulation 30 stderr 2.408 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label minimax/MiniMax-M3.1-flash Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/scratch/minimax~1MiniMax-M3.1-flash` | | | | | | | | 16 | [MiMo-V2.6-Pro](https://benchize.com/models/mimo-v2-6-pro.md) | 62.82% | SE ±3.55 pp | $0.29 | 3,235.5source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 62.815 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.287515 \| USD \| per_test \| Lower is better \| \| `latency` \| 3235.496 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Xiaomi reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.55 pp sourcePopulation 30 stderr 3.554 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label xiaomi/mimo-v2.6-pro Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/scratch/xiaomi~1mimo-v2.6-pro` | | | | | | | | 17 | [Muse Spark Open](https://benchize.com/models/muse-spark-open-xhigh.md)Extra high | 61.72% | SE ±2.7 pp | $3.69 | 4,418.17source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 61.72 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.688473 \| USD \| per_test \| Lower is better \| \| `latency` \| 4418.173 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 131072 provider Meta reasoning Not reported Reasoning effort xhigh Temperature 1 topP 1 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.7 pp sourcePopulation 30 stderr 2.699 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label meta/muse-spark-open Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/scratch/meta~1muse-spark-open` | | | | | | | | 18 | [MiniMax M3](https://benchize.com/models/minimax-m3.md) | 59.21% | SE ±2.79 pp | $3.22 | 1,360.38source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 59.207 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.220244 \| USD \| per_test \| Lower is better \| \| `latency` \| 1360.375 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.79 pp sourcePopulation 30 stderr 2.794 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/scratch/minimax~1MiniMax-M3` | | | | | | | | 19 | [Claude Haiku 5.5](https://benchize.com/models/claude-haiku-5-5-max.md)Max | 57.65% | SE ±4.55 pp | $1.33 | 1,210.58source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 57.654 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.331689 \| USD \| per_test \| Lower is better \| \| `latency` \| 1210.577 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.55 pp sourcePopulation 30 stderr 4.548 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/scratch/anthropic~1claude-haiku-5-5` | | | | | | | --- Cite as: EMB v1.1 / scratch — Benchize, https://benchize.com/benchmarks/vals-ai%3Aemb-v1-1%3Ascratch (retrieved 2026-10-21)