Model comparison
Command A vs Mistral Large
Command A is the stronger model overall, scoring 36.5 to 31.9 on the Noometry Index.
Last verified . 22 shared benchmarks.
Cohere
Mistral AISummary
- They share 22 benchmarks with published results for both. Command A scores higher in 8 categories and Mistral Large in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Command A leads 36.2 to 18.2.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 57.1% for Command A and 38.4% for Mistral Large.
- Mistral Large is cheaper at $2 / $6 per million input/output tokens, against $2.50 / $10 for Command A.
- Command A accepts more context: 256K tokens versus 131K.
Side by side
| Command A | Mistral Large | |
|---|---|---|
| Provider | Cohere | Mistral AI |
| Noometry Index | 36.5 | 31.9 |
| Released | 2025-03-13 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 256K | 131K |
| Max output | 8K | 16K |
| Input $ / M tokens | $2.50 | $2 |
| Output $ / M tokens | $10 | $6 |
| Results tracked | 24 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large leads
Command A: 27.2 (#322), Mistral Large: 34.3 (#240)
| Benchmark | Command A | Mistral Large |
|---|---|---|
| LMArena Coding | 1330 | 1277 |
| Aider Polyglot | 12% | — |
| SciCode | — | 36.2% |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| ALE-Bench | — | 264.7 |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use Command A leads
Command A: 35.9 (#40), Mistral Large: 28.6 (#89)
| Benchmark | Command A | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | 38.4% |
Reasoning Command A leads
Command A: 18.3 (#283), Mistral Large: 15.8 (#310)
| Benchmark | Command A | Mistral Large |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1257 |
| DTBench | 61.3% | 65.1% |
| LMCA | 10.3% | 16.7% |
| SimpleBench | — | 22.5% |
| Kagi LLM Benchmark | 28.8% | — |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 43.5% |
| LiveBench Data Analysis | — | 50.1% |
| Epoch Capabilities Index | — | 128.52 |
| ForecastBench | — | 57.1 |
| LiveBench | — | 48.4% |
Math Command A leads
Command A: 36.2 (#171), Mistral Large: 18.2 (#291)
| Benchmark | Command A | Mistral Large |
|---|---|---|
| LMArena Math | 1300 | 1262 |
| OTIS Mock AIME 2024-2025 | — | 8.5% |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Command A leads
Command A: 37.1 (#159), Mistral Large: 30.1 (#230)
| Benchmark | Command A | Mistral Large |
|---|---|---|
| Vectara Hallucination Rate | 9.3% | 4.5% |
| LMArena Expert | 1295 | 1232 |
| GPQA Diamond | — | 51.3% |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| GPQA (HELM) | — | 43.5% |
| MMLU | — | 80% |
Multilingual Command A leads
Command A: 45.3 (#170), Mistral Large: 40.0 (#219)
| Benchmark | Command A | Mistral Large |
|---|---|---|
| LMArena Non-English | 1313 | 1237 |
| LMArena Chinese | 1327 | 1240 |
| LMArena French | 1351 | 1325 |
| LMArena German | 1341 | 1254 |
| LMArena Japanese | 1285 | 1188 |
| LMArena Korean | 1285 | 1202 |
| LMArena Russian | 1314 | 1257 |
| LMArena Spanish | 1347 | 1268 |
Instruction Following Command A leads
Command A: 69.1 (#177), Mistral Large: 67.9 (#191)
| Benchmark | Command A | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1309 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |
Long Context Command A leads
Command A: 40.6 (#151), Mistral Large: 38.3 (#199)
| Benchmark | Command A | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1334 | 1261 |
Writing & Preference Command A leads
Command A: 47.6 (#208), Mistral Large: 40.7 (#242)
| Benchmark | Command A | Mistral Large |
|---|---|---|
| LMArena Text | 1331 | 1266 |
| LMArena Creative Writing | 1319 | 1243 |
| EQ-Bench Creative Writing | 1145 | 985 |
| LMArena Multi-Turn | 1339 | 1260 |
| Short-Story Creative Writing | — | 69% |
| WildBench | — | 80.1% |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is Command A better than Mistral Large?
Command A is the stronger model overall, scoring 36.5 to 31.9 on the Noometry Index.
Which is cheaper, Command A or Mistral Large?
Mistral Large is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; Command A lists at $2.50 and $10.
Is Command A or Mistral Large better for coding?
Mistral Large scores higher on coding benchmarks: 34.3 versus 27.2 in the Noometry coding category.
Which has the bigger context window?
Command A does, with 256K tokens against 131K.
How many benchmarks do Command A and Mistral Large share?
22 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Mistral Large has 51.