# Command A

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

Cohere

Canonical URL: https://benchize.com/models/command-a
Last updated: Thu, 22 Oct 2026 05:30:58 GMT

Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations.

Cohere

## Benchmarks

| Benchmark | Score | ± | Rank | Cost | Latency | Source |  |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [AIME 2025](https://benchize.com/benchmarks/aime-2025.md) | 11.67% | SE ±1.09 pp | 13 / 14 | $0.01 | 23.2source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_aime.C3_jItdR.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 11.667 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.010479 \| USD \| per_test \| Lower is better \| \| `latency` \| 23.196 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.09 pp sourcePopulation 96 stderr 1.091 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_aime.C3_jItdR.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:17.157Z Evidence SHA-256 `7d016210b39d24351bbb5d12be09a973decac461bb2486eb1f23724fed2b7e6c` Source locator `/tasks/aime_2025/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [MGSM / mgsm fr](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_fr.md) | 85.6% | SE ±2.22 pp | 4 / 8 | $0.00253 | 4.64source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 85.6 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002533 \| USD \| per_test \| Lower is better \| \| `latency` \| 4.639 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.22 pp sourcePopulation 75 stderr 2.22 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_fr/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [GPQA Diamond](https://benchize.com/benchmarks/gpqa-diamond.md) | 48.49% | SE ±2.28 pp | 36 / 40 | $0.01 | 11.49source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_gpqa.ghZZBpyU.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 48.485 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.010094 \| USD \| per_test \| Lower is better \| \| `latency` \| 11.49 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.28 pp sourcePopulation 138 stderr 2.276 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_gpqa.ghZZBpyU.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:20.661Z Evidence SHA-256 `951eb5224097733a9d09d06c14908ae2980e2e640e539f2c284877c5092d7077` Source locator `/tasks/overall/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [LegalBench / rule tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Arule_tasks.md) | 73.6% | SE ±1.56 pp | 37 / 44 | — | 1.39source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 73.598 \| percent \| reported \| Higher is better \| \| `latency` \| 1.385 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.56 pp sourcePopulation 151 stderr 1.556 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:08.909Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/rule_tasks/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [Arena text / industry life and physical and social science](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_life_and_physical_and_social_science.md) | 1,339.05 | — | 119 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1339.0500468307816 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text ### Reported statistics lower 1332.5064380408603 rank 225 upper 1345.593655620703 variance 11.146498763664624 votes 9387 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5722/row` |  |  |  |  |  |  |  |
| [Terminal-Bench 2.0 / hard](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-2%3Ahard.md) | 3.33% | SE ±3.33 pp | 19 / 23 | $7.23 | 2,256.67source duration | [Vals AI · 2.0](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2.T48tPR4O.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 3.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.229384 \| USD \| per_test \| Lower is better \| \| `latency` \| 2256.665 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.33 pp sourcePopulation 67 stderr 3.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2.T48tPR4O.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 2.0 Observed 2026-10-22T02:10:29.313Z Evidence SHA-256 `38e640d995259778e531f048b2f2c7b3b281cb05b56be643ddc9dc53eb85adf7` Source locator `/tasks/hard/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [MedQA / overall](https://benchize.com/benchmarks/vals-ai%3Amedqa%3Aoverall.md) | 80.55% | SE ±0.36 pp | 9 / 12 | $0.00346 | 2.91source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 80.55 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.003459 \| USD \| per_test \| Lower is better \| \| `latency` \| 2.908 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.36 pp sourcePopulation 95 stderr 0.361 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:15.908Z Evidence SHA-256 `d67905978d932f64698ebe9e230d9519e5bae1c9d7176dda8379dc3874b6f90f` Source locator `/tasks/overall/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [Arena text / industry entertainment and sports and media](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_entertainment_and_sports_and_media.md) | 1,306.43 | — | 110 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1306.4251292224064 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text ### Reported statistics lower 1300.20115154215 rank 209 upper 1312.6491069026629 variance 10.084163327652412 votes 10061 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4901/row` |  |  |  |  |  |  |  |
| [CorpFin v2 / overall](https://benchize.com/benchmarks/vals-ai%3Acorp_fin_v2%3Aoverall.md) | 45.96% | SE ±0.97 pp | 36 / 39 | $0.21 | 14.15source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 45.96 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.206138 \| USD \| per_test \| Lower is better \| \| `latency` \| 14.146 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.97 pp sourcePopulation 134 stderr 0.972 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 2 Observed 2026-10-22T02:10:13.429Z Evidence SHA-256 `7cf2217ab3728d5a84bffce82aab9fc52d7f810b0cbe8c65b387df47f3d31c9b` Source locator `/tasks/overall/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [MMLU Pro / psychology](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Apsychology.md) | 74.69% | SE ±1.61 pp | 39 / 40 | $0.00589 | 7.09source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 74.687 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.005887 \| USD \| per_test \| Lower is better \| \| `latency` \| 7.087 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.61 pp sourcePopulation 138 stderr 1.612 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/psychology/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [AIME / aime 2024](https://benchize.com/benchmarks/vals-ai%3Aaime%3Aaime_2024.md) | 15% | SE ±1.54 pp | 11 / 14 | $0.01 | 23.49source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_aime.C3_jItdR.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 15 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.012986 \| USD \| per_test \| Lower is better \| \| `latency` \| 23.494 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.54 pp sourcePopulation 96 stderr 1.543 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_aime.C3_jItdR.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:17.157Z Evidence SHA-256 `7d016210b39d24351bbb5d12be09a973decac461bb2486eb1f23724fed2b7e6c` Source locator `/tasks/aime_2024/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [MGSM / mgsm sw](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_sw.md) | 74.4% | SE ±2.76 pp | 8 / 8 | $0.00274 | 3.98source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 74.4 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002741 \| USD \| per_test \| Lower is better \| \| `latency` \| 3.983 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.76 pp sourcePopulation 75 stderr 2.76 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_sw/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [TaxEval v2 / stepwise reasoning](https://benchize.com/benchmarks/vals-ai%3Atax_eval_v2%3Astepwise_reasoning.md) | 73.75% | SE ±1.26 pp | 37 / 40 | $0.00648 | 11.21source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_tax_eval_v2.B3yoffr8.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 73.753 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.006484 \| USD \| per_test \| Lower is better \| \| `latency` \| 11.214 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.26 pp sourcePopulation 145 stderr 1.258 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_eval_v2.B3yoffr8.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 2 Observed 2026-10-22T02:10:14.414Z Evidence SHA-256 `8b354a6ae848f5bb25a2e8b061b5f576d5b9e0c11b941dc1e6bed078e6529cd6` Source locator `/tasks/stepwise_reasoning/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [MedQA / hispanic](https://benchize.com/benchmarks/vals-ai%3Amedqa%3Ahispanic.md) | 79.7% | SE ±0.9 pp | 9 / 12 | $0.00348 | 2.91source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 79.7 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.003475 \| USD \| per_test \| Lower is better \| \| `latency` \| 2.911 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.9 pp sourcePopulation 95 stderr 0.899 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:15.908Z Evidence SHA-256 `d67905978d932f64698ebe9e230d9519e5bae1c9d7176dda8379dc3874b6f90f` Source locator `/tasks/hispanic/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [MGSM / mgsm es](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_es.md) | 92.8% | SE ±1.64 pp | 4 / 8 | $0.00246 | 11.81source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 92.8 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002455 \| USD \| per_test \| Lower is better \| \| `latency` \| 11.81 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.64 pp sourcePopulation 75 stderr 1.635 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_es/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [Arena text style control / creative writing](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acreative_writing.md) | 1,335.96 | — | 103 / 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` \| 1335.9603750693802 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text_style_control ### Reported statistics lower 1328.759067570437 rank 197 upper 1343.1616825683232 variance 13.499774985213419 votes 7604 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1418/row` |  |  |  |  |  |  |  |
| [Arena text / expert](https://benchize.com/benchmarks/lmarena%3Atext%3Aexpert.md) | 1,295.59 | — | 122 / 148 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1295.594521600534 \| rating \| reported \| Higher is better \| ### Configuration category expert config text ### Reported statistics lower 1284.4719248239244 rank 234 upper 1306.7171183771438 variance 32.20447356837613 votes 2884 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2704/row` |  |  |  |  |  |  |  |
| [MMLU Pro / math](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Amath.md) | 78.46% | SE ±1.13 pp | 36 / 40 | $0.00972 | 13.48source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 78.46 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.009716 \| USD \| per_test \| Lower is better \| \| `latency` \| 13.483 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.13 pp sourcePopulation 138 stderr 1.133 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/math/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [Arena text style control / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_medicine_and_healthcare.md) | 1,375.88 | — | 113 / 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` \| 1375.8780875162604 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text_style_control ### Reported statistics lower 1364.8092542233744 rank 212 upper 1386.9469208091464 variance 31.893891405444105 votes 3057 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6524/row` |  |  |  |  |  |  |  |
| [MMLU Pro / engineering](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Aengineering.md) | 55.52% | SE ±1.61 pp | 35 / 40 | $0.01 | 18.25source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 55.521 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.011655 \| USD \| per_test \| Lower is better \| \| `latency` \| 18.253 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.61 pp sourcePopulation 138 stderr 1.606 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/engineering/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [MMLU Pro / philosophy](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Aphilosophy.md) | 62.12% | SE ±2.18 pp | 38 / 40 | $0.00592 | 7.62source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 62.124 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.005916 \| USD \| per_test \| Lower is better \| \| `latency` \| 7.621 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.18 pp sourcePopulation 138 stderr 2.178 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/philosophy/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [MMLU Pro / health](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Ahealth.md) | 70.54% | SE ±1.68 pp | 38 / 40 | $0.00618 | 6.74source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 70.538 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.006182 \| USD \| per_test \| Lower is better \| \| `latency` \| 6.736 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.68 pp sourcePopulation 138 stderr 1.683 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/health/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [CorpFin v2 / max fitting context](https://benchize.com/benchmarks/vals-ai%3Acorp_fin_v2%3Amax_fitting_context.md) | 41.96% | SE ±1.69 pp | 37 / 39 | $0.45 | 27.75source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 41.958 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.445899 \| USD \| per_test \| Lower is better \| \| `latency` \| 27.747 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.69 pp sourcePopulation 134 stderr 1.685 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 2 Observed 2026-10-22T02:10:13.429Z Evidence SHA-256 `7cf2217ab3728d5a84bffce82aab9fc52d7f810b0cbe8c65b387df47f3d31c9b` Source locator `/tasks/max_fitting_context/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [Arena text style control / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts_english.md) | 1,374.94 | — | 116 / 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` \| 1374.944823813219 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text_style_control ### Reported statistics lower 1368.904945184768 rank 226 upper 1380.9847024416704 variance 9.49642715155549 votes 11260 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4093/row` |  |  |  |  |  |  |  |
| [Arena text / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts_english.md) | 1,335.03 | — | 123 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1335.0278292114772 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text ### Reported statistics lower 1329.0026716328828 rank 237 upper 1341.0529867900718 variance 9.450192112260062 votes 11260 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4104/row` |  |  |  |  |  |  |  |
| [LegalBench / conclusion tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Aconclusion_tasks.md) | 83.08% | SE ±0.96 pp | 37 / 44 | — | 0.57source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 83.079 \| percent \| reported \| Higher is better \| \| `latency` \| 0.573 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.96 pp sourcePopulation 151 stderr 0.962 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:08.909Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/conclusion_tasks/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [Arena text / russian](https://benchize.com/benchmarks/lmarena%3Atext%3Arussian.md) | 1,313.91 | — | 117 / 150 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1313.9096174879578 \| rating \| reported \| Higher is better \| ### Configuration category russian config text ### Reported statistics lower 1305.2298475300508 rank 221 upper 1322.5893874458648 variance 19.611926103784832 votes 4471 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10604/row` |  |  |  |  |  |  |  |
| [Arena text / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_medicine_and_healthcare.md) | 1,334.49 | — | 119 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1334.4875297440024 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text ### Reported statistics lower 1323.4664915833844 rank 224 upper 1345.5085679046203 variance 31.61905094061401 votes 3057 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6536/row` |  |  |  |  |  |  |  |
| [Arena text style control / non english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Anon_english.md) | 1,336.26 | — | 115 / 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` \| 1336.261710267576 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text_style_control ### Reported statistics lower 1331.9071114656183 rank 214 upper 1340.6163090695338 variance 4.936283743004038 votes 29463 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9944/row` |  |  |  |  |  |  |  |
| [Arena text style control / french](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Afrench.md) | 1,381.99 | — | 103 / 132 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1381.9919979490824 \| rating \| reported \| Higher is better \| ### Configuration category french config text_style_control ### Reported statistics lower 1359.9436810076372 rank 186 upper 1404.040314890528 variance 126.54783056156552 votes 776 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3023/row` |  |  |  |  |  |  |  |
| [LegalBench / interpretation tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Ainterpretation_tasks.md) | 77.41% | SE ±0.21 pp | 33 / 44 | — | 0.7source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 77.414 \| percent \| reported \| Higher is better \| \| `latency` \| 0.696 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.21 pp sourcePopulation 151 stderr 0.209 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:08.909Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/interpretation_tasks/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [Berkeley Function Calling Leaderboard](https://benchize.com/benchmarks/bfcl%3Aoverall.md) | 46.49% | — | 9 / 26 | $91.37 | 2.09s | [Berkeley Function Calling Leaderboard](https://api.github.com/repos/HuanzhiMao/BFCL-Result/contents/2025-12-16/score/data_overall.csv?ref=cadd76a8dc62984e7bf15ecaf358f070bae745cc) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 46.49 \| percent \| reported \| Higher is better \| \| `cost_total` \| 91.37 \| USD \| evaluation_total \| Lower is better \| \| `latency_mean` \| 2.09 \| seconds \| per_call_mean \| Lower is better \| \| `latency_sd` \| 7.36 \| seconds \| per_call_sd \| Lower is better \| \| `non_live_ast_acc` \| 87.56 \| percent \| reported_task_score \| Higher is better \| \| `non_live_simple_ast` \| 75.75 \| percent \| reported_task_score \| Higher is better \| \| `non_live_multiple_ast` \| 93 \| percent \| reported_task_score \| Higher is better \| \| `non_live_parallel_ast` \| 93.5 \| percent \| reported_task_score \| Higher is better \| \| `non_live_parallel_multiple_ast` \| 88 \| percent \| reported_task_score \| Higher is better \| \| `live_acc` \| 78.53 \| percent \| reported_task_score \| Higher is better \| \| `live_simple_ast` \| 85.66 \| percent \| reported_task_score \| Higher is better \| \| `live_multiple_ast` \| 76.92 \| percent \| reported_task_score \| Higher is better \| \| `live_parallel_ast` \| 81.25 \| percent \| reported_task_score \| Higher is better \| \| `live_parallel_multiple_ast` \| 70.83 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_acc` \| 29.5 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_base` \| 38 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_miss_func` \| 23 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_miss_param` \| 32 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_long_context` \| 25 \| percent \| reported_task_score \| Higher is better \| \| `web_search_acc` \| 46.5 \| percent \| reported_task_score \| Higher is better \| \| `web_search_base` \| 60 \| percent \| reported_task_score \| Higher is better \| \| `web_search_no_snippet` \| 33 \| percent \| reported_task_score \| Higher is better \| \| `memory_acc` \| 16.56 \| percent \| reported_task_score \| Higher is better \| \| `memory_kv` \| 4.52 \| percent \| reported_task_score \| Higher is better \| \| `memory_vector` \| 5.16 \| percent \| reported_task_score \| Higher is better \| \| `memory_recursive_summarization` \| 40 \| percent \| reported_task_score \| Higher is better \| \| `relevance_detection` \| 81.25 \| percent \| reported_task_score \| Higher is better \| \| `irrelevance_detection` \| 84.19 \| percent \| reported_task_score \| Higher is better \| \| `latency_p95` \| 4.94 \| seconds \| per_call_p95 \| Lower is better \| ### Configuration mode FC sourceRelease 2025-12-16 ### Reported statistics rank 35 ### Source [Original source](https://api.github.com/repos/HuanzhiMao/BFCL-Result/contents/2025-12-16/score/data_overall.csv?ref=cadd76a8dc62984e7bf15ecaf358f070bae745cc) Source Berkeley Function Calling Leaderboard Original model label Command A Observed 2026-10-22T02:40:09.731Z Evidence SHA-256 `ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6` Source locator `/rows/35` |  |  |  |  |  |  |  |
| [MMLU Pro / computer science](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Acomputer_science.md) | 70.98% | SE ±2.37 pp | 39 / 40 | $0.0082 | 8.32source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 70.976 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.008203 \| USD \| per_test \| Lower is better \| \| `latency` \| 8.315 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.37 pp sourcePopulation 138 stderr 2.368 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/computer_science/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [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) | 1,370.64 | — | 113 / 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` \| 1370.6428470320534 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text_style_control ### Reported statistics lower 1364.0780946104528 rank 214 upper 1377.2075994536542 variance 11.218648010685971 votes 9387 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5711/row` |  |  |  |  |  |  |  |
| [Arena text style control / chinese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Achinese.md) | 1,359.85 | — | 118 / 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` \| 1359.8536459392815 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text_style_control ### Reported statistics lower 1349.90031606932 rank 232 upper 1369.8069758092429 variance 25.789362876045303 votes 3821 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/648/row` |  |  |  |  |  |  |  |
| [Arena text / german](https://benchize.com/benchmarks/lmarena%3Atext%3Agerman.md) | 1,341.67 | — | 98 / 129 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1341.6671101614302 \| rating \| reported \| Higher is better \| ### Configuration category german config text ### Reported statistics lower 1325.4359557543714 rank 176 upper 1357.8982645684891 variance 68.58081413409016 votes 1371 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3312/row` |  |  |  |  |  |  |  |
| [MMLU Pro / chemistry](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Achemistry.md) | 68.91% | SE ±1.4 pp | 38 / 40 | $0.01 | 17.16source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 68.905 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.010878 \| USD \| per_test \| Lower is better \| \| `latency` \| 17.157 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.4 pp sourcePopulation 138 stderr 1.404 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/chemistry/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [Arena text / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_legal_and_government.md) | 1,347.71 | — | 114 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1347.7071403716936 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text ### Reported statistics lower 1337.4080215585507 rank 210 upper 1358.0062591848364 variance 27.61238718890299 votes 3432 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5317/row` |  |  |  |  |  |  |  |
| [Arena text / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_business_and_management_and_financial_operations.md) | 1,314.8 | — | 118 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1314.7990456081602 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text ### Reported statistics lower 1308.0055327529642 rank 227 upper 1321.592558463356 variance 12.014138135515111 votes 8783 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4509/row` |  |  |  |  |  |  |  |
| [Arena text / korean](https://benchize.com/benchmarks/lmarena%3Atext%3Akorean.md) | 1,284.97 | — | 97 / 124 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1284.96905063198 \| rating \| reported \| Higher is better \| ### Configuration category korean config text ### Reported statistics lower 1266.6924727499554 rank 181 upper 1303.245628514005 variance 86.95480406512895 votes 1116 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8414/row` |  |  |  |  |  |  |  |
| [TaxEval v2 / correctness](https://benchize.com/benchmarks/vals-ai%3Atax_eval_v2%3Acorrectness.md) | 48.98% | SE ±1.43 pp | 38 / 40 | $0.00648 | 11.21source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_tax_eval_v2.B3yoffr8.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 48.978 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.006484 \| USD \| per_test \| Lower is better \| \| `latency` \| 11.214 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.43 pp sourcePopulation 145 stderr 1.429 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_eval_v2.B3yoffr8.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 2 Observed 2026-10-22T02:10:14.414Z Evidence SHA-256 `8b354a6ae848f5bb25a2e8b061b5f576d5b9e0c11b941dc1e6bed078e6529cd6` Source locator `/tasks/correctness/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [Arena text style control / russian](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Arussian.md) | 1,340.77 | — | 114 / 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` \| 1340.767917211229 \| rating \| reported \| Higher is better \| ### Configuration category russian config text_style_control ### Reported statistics lower 1332.0446698702667 rank 217 upper 1349.4911645521913 variance 19.808892330610977 votes 4471 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10600/row` |  |  |  |  |  |  |  |
| [Arena text / instruction following](https://benchize.com/benchmarks/lmarena%3Atext%3Ainstruction_following.md) | 1,308.74 | — | 117 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1308.7446845126224 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text ### Reported statistics lower 1303.466825745922 rank 227 upper 1314.0225432793227 variance 7.251358002635718 votes 15575 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7760/row` |  |  |  |  |  |  |  |
| [Arena text / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext%3Aexclude_ties.md) | 1,281.22 | — | 119 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1281.2163110832314 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text ### Reported statistics lower 1276.3091461386787 rank 228 upper 1286.123476027784 variance 6.268521652067374 votes 38475 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2281/row` |  |  |  |  |  |  |  |
| [MGSM / mgsm en](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_en.md) | 97.6% | SE ±0.97 pp | 4 / 8 | $0.00238 | 4.65source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 97.6 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002382 \| USD \| per_test \| Lower is better \| \| `latency` \| 4.648 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.97 pp sourcePopulation 75 stderr 0.968 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_en/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [Arena text style control / overall](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aoverall.md) | 1,353.73 | — | 113 / 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` \| 1353.7292597771407 \| rating \| reported \| Higher is better \| ### Configuration category overall config text_style_control ### Reported statistics lower 1350.257964711752 rank 213 upper 1357.2005548425295 variance 3.1368003650276357 votes 55769 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/212/row` |  |  |  |  |  |  |  |
| [GPQA Diamond / diamond zero shot cot](https://benchize.com/benchmarks/vals-ai%3Agpqa%3Adiamond_zero_shot_cot.md) | 46.97% | SE ±3.07 pp | 37 / 40 | $0.00778 | 11.09source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_gpqa.ghZZBpyU.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 46.97 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.00778 \| USD \| per_test \| Lower is better \| \| `latency` \| 11.092 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.07 pp sourcePopulation 138 stderr 3.067 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_gpqa.ghZZBpyU.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:20.661Z Evidence SHA-256 `951eb5224097733a9d09d06c14908ae2980e2e640e539f2c284877c5092d7077` Source locator `/tasks/diamond_zero_shot_cot/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [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) | 1,329.72 | — | 105 / 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` \| 1329.7160388736334 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text_style_control ### Reported statistics lower 1323.456569497613 rank 199 upper 1335.9755082496536 variance 10.199499382439274 votes 10061 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4891/row` |  |  |  |  |  |  |  |
| [Arena text style control / industry writing and literature and language](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_writing_and_literature_and_language.md) | 1,348.13 | — | 104 / 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` \| 1348.130344668606 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text_style_control ### Reported statistics lower 1342.3506836902568 rank 197 upper 1353.9100056469551 variance 8.69578006269435 votes 12803 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7314/row` |  |  |  |  |  |  |  |
| [MedQA / unbiased](https://benchize.com/benchmarks/vals-ai%3Amedqa%3Aunbiased.md) | 82.7% | SE ±0.85 pp | 7 / 12 | $0.00338 | 2.86source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 82.7 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.003378 \| USD \| per_test \| Lower is better \| \| `latency` \| 2.861 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.85 pp sourcePopulation 95 stderr 0.846 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:15.908Z Evidence SHA-256 `d67905978d932f64698ebe9e230d9519e5bae1c9d7176dda8379dc3874b6f90f` Source locator `/tasks/unbiased/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [Arena text / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_software_and_it_services.md) | 1,336.5 | — | 123 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1336.496162181635 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text ### Reported statistics lower 1331.4245560070278 rank 236 upper 1341.5677683562426 variance 6.6956826536196346 votes 17976 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6936/row` |  |  |  |  |  |  |  |
| [TaxEval v2 / overall](https://benchize.com/benchmarks/vals-ai%3Atax_eval_v2%3Aoverall.md) | 61.37% | SE ±0.95 pp | 37 / 40 | $0.00648 | 11.21source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_tax_eval_v2.B3yoffr8.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 61.366 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.006484 \| USD \| per_test \| Lower is better \| \| `latency` \| 11.214 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.95 pp sourcePopulation 145 stderr 0.952 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_eval_v2.B3yoffr8.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 2 Observed 2026-10-22T02:10:14.414Z Evidence SHA-256 `8b354a6ae848f5bb25a2e8b061b5f576d5b9e0c11b941dc1e6bed078e6529cd6` Source locator `/tasks/overall/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [Arena text style control / instruction following](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ainstruction_following.md) | 1,341.92 | — | 114 / 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` \| 1341.924834119384 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1336.6206146650877 rank 217 upper 1347.2290535736804 variance 7.323973868409878 votes 15575 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7750/row` |  |  |  |  |  |  |  |
| [Arena text style control / korean](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Akorean.md) | 1,315.41 | — | 95 / 124 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1315.408402888186 \| rating \| reported \| Higher is better \| ### Configuration category korean config text_style_control ### Reported statistics lower 1297.0765016038645 rank 175 upper 1333.7403041725072 variance 87.4820271110903 votes 1116 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8408/row` |  |  |  |  |  |  |  |
| [Terminal-Bench 2.0 / overall](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-2%3Aoverall.md) | 2.25% | SE ±1.58 pp | 23 / 23 | $2.44 | 760.67source duration | [Vals AI · 2.0](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2.T48tPR4O.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 2.247 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.436871 \| USD \| per_test \| Lower is better \| \| `latency` \| 760.674 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.58 pp sourcePopulation 67 stderr 1.58 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2.T48tPR4O.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 2.0 Observed 2026-10-22T02:10:29.313Z Evidence SHA-256 `38e640d995259778e531f048b2f2c7b3b281cb05b56be643ddc9dc53eb85adf7` Source locator `/tasks/overall/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [Arena text style control / expert](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexpert.md) | 1,344.14 | — | 119 / 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` \| 1344.137113593435 \| rating \| reported \| Higher is better \| ### Configuration category expert config text_style_control ### Reported statistics lower 1332.9286823878106 rank 227 upper 1355.3455447990598 variance 32.70344313323091 votes 2884 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2697/row` |  |  |  |  |  |  |  |
| [LiveCodeBench / overall](https://benchize.com/benchmarks/vals-ai%3Alcb%3Aoverall.md) | 35.07% | SE ±1.09 pp | 42 / 43 | $0.00657 | 11.75source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 35.071 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.006568 \| USD \| per_test \| Lower is better \| \| `latency` \| 11.746 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.09 pp sourcePopulation 143 stderr 1.086 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:28.824Z Evidence SHA-256 `1a7c7dabc9d95a0182886b1edc42623987cac2095a0d407a5e334f37acdfa2f5` Source locator `/tasks/overall/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [Arena text style control / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_legal_and_government.md) | 1,377.16 | — | 108 / 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` \| 1377.1627205879913 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text_style_control ### Reported statistics lower 1366.8125333594362 rank 205 upper 1387.5129078165467 variance 27.886899395889188 votes 3432 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5312/row` |  |  |  |  |  |  |  |
| [MATH-500](https://benchize.com/benchmarks/math-500.md) | 76.2% | SE ±1.9 pp | 2 / 5 | $0.00598 | 8.67source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_math500.BvFbu92X.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 76.2 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.005983 \| USD \| per_test \| Lower is better \| \| `latency` \| 8.665 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8192 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.9 pp sourcePopulation 60 stderr 1.904 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_math500.BvFbu92X.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:17.658Z Evidence SHA-256 `435ec4da1112362c0a6bb4afeab53bf7b0faf2000e1ddbe1a878735dca1fe35b` Source locator `/tasks/overall/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [Arena text / chinese](https://benchize.com/benchmarks/lmarena%3Atext%3Achinese.md) | 1,327.34 | — | 120 / 146 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1327.3425738060798 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text ### Reported statistics lower 1317.427538373578 rank 233 upper 1337.2576092385814 variance 25.59130065332806 votes 3821 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/649/row` |  |  |  |  |  |  |  |
| [Arena text style control / spanish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aspanish.md) | 1,367.01 | — | 105 / 134 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1367.0110094029733 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text_style_control ### Reported statistics lower 1349.4022505641092 rank 193 upper 1384.619768241837 variance 80.71631177585726 votes 1179 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10957/row` |  |  |  |  |  |  |  |
| [LiveCodeBench / medium](https://benchize.com/benchmarks/vals-ai%3Alcb%3Amedium.md) | 23.76% | SE ±2.18 pp | 42 / 43 | $0.00684 | 7.85source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 23.76 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.006843 \| USD \| per_test \| Lower is better \| \| `latency` \| 7.849 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.18 pp sourcePopulation 143 stderr 2.175 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:28.824Z Evidence SHA-256 `1a7c7dabc9d95a0182886b1edc42623987cac2095a0d407a5e334f37acdfa2f5` Source locator `/tasks/medium/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [Arena text / longer query](https://benchize.com/benchmarks/lmarena%3Atext%3Alonger_query.md) | 1,334.2 | — | 110 / 150 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1334.1959604615774 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text ### Reported statistics lower 1328.0997475050704 rank 210 upper 1340.2921734180845 variance 9.674400832017612 votes 10708 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8727/row` |  |  |  |  |  |  |  |
| [Terminal-Bench 2.0 / easy](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-2%3Aeasy.md) | 0% | SE ±0 pp | 23 / 23 | $54.22 | 16,924.99source duration | [Vals AI · 2.0](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2.T48tPR4O.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 54.220382 \| USD \| per_test \| Lower is better \| \| `latency` \| 16924.986 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 67 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2.T48tPR4O.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 2.0 Observed 2026-10-22T02:10:29.313Z Evidence SHA-256 `38e640d995259778e531f048b2f2c7b3b281cb05b56be643ddc9dc53eb85adf7` Source locator `/tasks/easy/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [Arena text style control / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_mathematical.md) | 1,326.68 | — | 125 / 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` \| 1326.675176287546 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text_style_control ### Reported statistics lower 1317.0558426041905 rank 235 upper 1336.2945099709018 variance 24.087614843940845 votes 3654 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6147/row` |  |  |  |  |  |  |  |
| [SWE-bench / 1-4 hours](https://benchize.com/benchmarks/vals-ai%3Aswebench%3A1-4%20hours.md) | 0% | SE ±0 pp | 39 / 39 | $0.15 | 191.35source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.150556 \| USD \| per_test \| Lower is better \| \| `latency` \| 191.352 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 88 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:28.317Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/1-4 hours/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [MGSM / mgsm ja](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_ja.md) | 86.8% | SE ±2.14 pp | 6 / 8 | $0.00228 | 4.28source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 86.8 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002281 \| USD \| per_test \| Lower is better \| \| `latency` \| 4.279 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.14 pp sourcePopulation 75 stderr 2.141 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_ja/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [Arena text / overall](https://benchize.com/benchmarks/lmarena%3Atext.md) | 1,330.97 | — | 119 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1330.970709042806 \| rating \| reported \| Higher is better \| ### Configuration category overall config text ### Reported statistics lower 1327.5219263752335 rank 226 upper 1334.4194917103785 variance 3.096246099027334 votes 55769 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/225/row` |  |  |  |  |  |  |  |
| [MGSM / mgsm ru](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_ru.md) | 95.2% | SE ±1.35 pp | 3 / 8 | $0.00246 | 11.51source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 95.2 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002456 \| USD \| per_test \| Lower is better \| \| `latency` \| 11.513 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.35 pp sourcePopulation 75 stderr 1.352 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_ru/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [Arena text / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_mathematical.md) | 1,312.14 | — | 124 / 148 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1312.135235643426 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text ### Reported statistics lower 1302.5242950125216 rank 234 upper 1321.7461762743305 variance 24.04559937312582 votes 3654 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6146/row` |  |  |  |  |  |  |  |
| [LegalBench / rhetoric tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Arhetoric_tasks.md) | 79.6% | SE ±0.83 pp | 28 / 44 | — | 0.57source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 79.598 \| percent \| reported \| Higher is better \| \| `latency` \| 0.57 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.83 pp sourcePopulation 151 stderr 0.826 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:08.909Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/rhetoric_tasks/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [MedQA / white](https://benchize.com/benchmarks/vals-ai%3Amedqa%3Awhite.md) | 80.65% | SE ±0.88 pp | 9 / 12 | $0.00347 | 2.95source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 80.65 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.00347 \| USD \| per_test \| Lower is better \| \| `latency` \| 2.947 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.88 pp sourcePopulation 95 stderr 0.883 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:15.908Z Evidence SHA-256 `d67905978d932f64698ebe9e230d9519e5bae1c9d7176dda8379dc3874b6f90f` Source locator `/tasks/white/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [Arena text / spanish](https://benchize.com/benchmarks/lmarena%3Atext%3Aspanish.md) | 1,347.35 | — | 109 / 134 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1347.3530069551357 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text ### Reported statistics lower 1329.8582790444789 rank 197 upper 1364.8477348657925 variance 79.67429014704575 votes 1179 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10961/row` |  |  |  |  |  |  |  |
| [MGSM / mgsm bn](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_bn.md) | 84.4% | SE ±2.3 pp | 3 / 8 | $0.00616 | 14.94source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 84.4 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.006158 \| USD \| per_test \| Lower is better \| \| `latency` \| 14.944 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.3 pp sourcePopulation 75 stderr 2.295 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_bn/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [Arena text / japanese](https://benchize.com/benchmarks/lmarena%3Atext%3Ajapanese.md) | 1,285.38 | — | 93 / 120 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1285.3834080268584 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text ### Reported statistics lower 1267.5239874845213 rank 171 upper 1303.2428285691956 variance 83.03067063736461 votes 1236 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8121/row` |  |  |  |  |  |  |  |
| [MGSM / mgsm zh](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_zh.md) | 90.4% | SE ±1.86 pp | 5 / 8 | $0.00222 | 9.79source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 90.4 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002222 \| USD \| per_test \| Lower is better \| \| `latency` \| 9.789 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.86 pp sourcePopulation 75 stderr 1.863 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_zh/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [MGSM / overall](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Aoverall.md) | 85.71% | SE ±2.02 pp | 7 / 8 | $0.00373 | 8.36source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 85.709 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.003732 \| USD \| per_test \| Lower is better \| \| `latency` \| 8.36 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.02 pp sourcePopulation 75 stderr 2.016 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/overall/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [LiveCodeBench / easy](https://benchize.com/benchmarks/vals-ai%3Alcb%3Aeasy.md) | 78.88% | SE ±2.28 pp | 42 / 43 | $0.0044 | 20.39source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 78.882 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.004396 \| USD \| per_test \| Lower is better \| \| `latency` \| 20.386 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.28 pp sourcePopulation 143 stderr 2.275 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:28.824Z Evidence SHA-256 `1a7c7dabc9d95a0182886b1edc42623987cac2095a0d407a5e334f37acdfa2f5` Source locator `/tasks/easy/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [Arena text / french](https://benchize.com/benchmarks/lmarena%3Atext%3Afrench.md) | 1,351.42 | — | 107 / 132 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1351.4191929130332 \| rating \| reported \| Higher is better \| ### Configuration category french config text ### Reported statistics lower 1329.380864355381 rank 190 upper 1373.4575214706852 variance 126.43319850224488 votes 776 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3027/row` |  |  |  |  |  |  |  |
| [Arena text / english](https://benchize.com/benchmarks/lmarena%3Atext%3Aenglish.md) | 1,343.58 | — | 120 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1343.5806116766041 \| rating \| reported \| Higher is better \| ### Configuration category english config text ### Reported statistics lower 1339.1257105149857 rank 234 upper 1348.0355128382225 variance 5.166304075127972 votes 26256 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1870/row` |  |  |  |  |  |  |  |
| [MMLU Pro / economics](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Aeconomics.md) | 77.73% | SE ±1.54 pp | 39 / 40 | $0.00669 | 5.89source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 77.725 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.006694 \| USD \| per_test \| Lower is better \| \| `latency` \| 5.885 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.54 pp sourcePopulation 138 stderr 1.535 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/economics/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [CorpFin v2 / exact pages](https://benchize.com/benchmarks/vals-ai%3Acorp_fin_v2%3Aexact_pages.md) | 56.18% | SE ±1.69 pp | 34 / 39 | $0.00564 | 3.83source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 56.177 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.005637 \| USD \| per_test \| Lower is better \| \| `latency` \| 3.828 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.69 pp sourcePopulation 134 stderr 1.694 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 2 Observed 2026-10-22T02:10:13.429Z Evidence SHA-256 `7cf2217ab3728d5a84bffce82aab9fc52d7f810b0cbe8c65b387df47f3d31c9b` Source locator `/tasks/exact_pages/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [Arena text style control / english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aenglish.md) | 1,365.51 | — | 115 / 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` \| 1365.5145035275714 \| rating \| reported \| Higher is better \| ### Configuration category english config text_style_control ### Reported statistics lower 1361.0349685459664 rank 224 upper 1369.9940385091763 variance 5.223597229085025 votes 26256 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1860/row` |  |  |  |  |  |  |  |
| [Terminal-Bench 2.0 / medium](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-2%3Amedium.md) | 1.82% | SE ±1.82 pp | 23 / 23 | $3.94 | 1,230.91source duration | [Vals AI · 2.0](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2.T48tPR4O.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 1.818 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.943301 \| USD \| per_test \| Lower is better \| \| `latency` \| 1230.908 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.82 pp sourcePopulation 67 stderr 1.818 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2.T48tPR4O.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 2.0 Observed 2026-10-22T02:10:29.313Z Evidence SHA-256 `38e640d995259778e531f048b2f2c7b3b281cb05b56be643ddc9dc53eb85adf7` Source locator `/tasks/medium/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [Arena text style control / japanese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ajapanese.md) | 1,306.53 | — | 90 / 120 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1306.52896135855 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text_style_control ### Reported statistics lower 1288.6390997370518 rank 169 upper 1324.4188229800482 variance 83.31396060065615 votes 1236 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8119/row` |  |  |  |  |  |  |  |
| [Arena text / multi turn](https://benchize.com/benchmarks/lmarena%3Atext%3Amulti_turn.md) | 1,338.46 | — | 112 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1338.4594782095137 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text ### Reported statistics lower 1331.8524098766322 rank 216 upper 1345.0665465423951 variance 11.363743305069873 votes 9291 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9531/row` |  |  |  |  |  |  |  |
| [MedQA / asian](https://benchize.com/benchmarks/vals-ai%3Amedqa%3Aasian.md) | 81.05% | SE ±0.88 pp | 8 / 12 | $0.00345 | 2.85source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 81.05 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.003452 \| USD \| per_test \| Lower is better \| \| `latency` \| 2.851 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.88 pp sourcePopulation 95 stderr 0.876 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:15.908Z Evidence SHA-256 `d67905978d932f64698ebe9e230d9519e5bae1c9d7176dda8379dc3874b6f90f` Source locator `/tasks/asian/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [Arena text style control / german](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Agerman.md) | 1,358.88 | — | 91 / 129 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1358.8794329909597 \| rating \| reported \| Higher is better \| ### Configuration category german config text_style_control ### Reported statistics lower 1342.598052574932 rank 168 upper 1375.1608134069872 variance 69.00590651223305 votes 1371 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3304/row` |  |  |  |  |  |  |  |
| [Arena text style control / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_software_and_it_services.md) | 1,379.84 | — | 116 / 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` \| 1379.8386262353786 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text_style_control ### Reported statistics lower 1374.7452011435917 rank 228 upper 1384.9320513271657 variance 6.753418525766734 votes 17976 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6928/row` |  |  |  |  |  |  |  |
| [MGSM / mgsm de](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_de.md) | 92.8% | SE ±1.64 pp | 3 / 8 | $0.00226 | 4.37source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 92.8 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002258 \| USD \| per_test \| Lower is better \| \| `latency` \| 4.368 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.64 pp sourcePopulation 75 stderr 1.635 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_de/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [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) | 1,351.71 | — | 110 / 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` \| 1351.7107870302934 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text_style_control ### Reported statistics lower 1344.9102091543564 rank 215 upper 1358.5113649062305 variance 12.03913971367999 votes 8783 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4497/row` |  |  |  |  |  |  |  |
| [Arena text / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts.md) | 1,326.37 | — | 122 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1326.365387240262 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text ### Reported statistics lower 1321.7327447593257 rank 230 upper 1330.9980297211982 variance 5.5867776690882 votes 23764 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3680/row` |  |  |  |  |  |  |  |
| [MMLU Pro / history](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Ahistory.md) | 64.04% | SE ±2.47 pp | 37 / 40 | $0.00917 | 5.9source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 64.042 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.009169 \| USD \| per_test \| Lower is better \| \| `latency` \| 5.903 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.47 pp sourcePopulation 138 stderr 2.474 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/history/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [MMLU Pro / law](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Alaw.md) | 51.41% | SE ±1.51 pp | 38 / 40 | $0.00814 | 8.48source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 51.408 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.008141 \| USD \| per_test \| Lower is better \| \| `latency` \| 8.478 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.51 pp sourcePopulation 138 stderr 1.506 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/law/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [Arena text style control / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexclude_ties.md) | 1,314.17 | — | 113 / 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` \| 1314.171513062121 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text_style_control ### Reported statistics lower 1309.1905572858434 rank 214 upper 1319.1524688383984 variance 6.4584632045461055 votes 38475 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2267/row` |  |  |  |  |  |  |  |
| [MMLU Pro / physics](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Aphysics.md) | 69.28% | SE ±1.3 pp | 39 / 40 | $0.00888 | 15.2source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 69.284 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.008877 \| USD \| per_test \| Lower is better \| \| `latency` \| 15.203 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.3 pp sourcePopulation 138 stderr 1.298 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/physics/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [MedQA / indigenous](https://benchize.com/benchmarks/vals-ai%3Amedqa%3Aindigenous.md) | 79.4% | SE ±0.9 pp | 10 / 12 | $0.00349 | 2.96source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 79.4 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.003488 \| USD \| per_test \| Lower is better \| \| `latency` \| 2.958 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.9 pp sourcePopulation 95 stderr 0.904 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:15.908Z Evidence SHA-256 `d67905978d932f64698ebe9e230d9519e5bae1c9d7176dda8379dc3874b6f90f` Source locator `/tasks/indigenous/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [MGSM / mgsm th](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_th.md) | 86.4% | SE ±2.17 pp | 7 / 8 | $0.00422 | 7.09source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 86.4 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.004219 \| USD \| per_test \| Lower is better \| \| `latency` \| 7.094 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.17 pp sourcePopulation 75 stderr 2.168 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_th/cohere~1command-a-03-2025` |  |  |  |  |  |  |  |
| [Arena text style control / polish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Apolish.md) | 1,349.84 | — | 96 / 117 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1349.843313097182 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1338.448033588928 rank 180 upper 1361.2385926054362 variance 33.80288612537361 votes 3071 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10327/row` |  |  |  |  |  |  |  |
| [Arena text style control / multi turn](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amulti_turn.md) | 1,360.36 | — | 105 / 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` \| 1360.3573235662575 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text_style_control ### Reported statistics lower 1353.7381690316363 rank 201 upper 1366.976478100879 variance 11.405356349825443 votes 9291 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9516/row` |  |  |  |  |  |  |  |

[Next page](https://benchize.com/models/command-a.md?cursor=d518929512be41e7c959a2f16ce5e16246aaff97540f6e9f8e89a80638f7a097)

---
Cite as: Command A — Benchize, https://benchize.com/models/command-a (retrieved 2026-10-22)