Model comparison
Codestral vs Command A
Command A is the stronger model overall, scoring 36.5 to 30.6 on the Noometry Index. Codestral costs 9.7× less per token, which makes it the better buy when Command A's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
Mistral AI
CohereSummary
- They share 2 benchmarks with published results for both. Codestral scores higher in 2 categories and Command A in 0 categories; one gap is clear of the uncertainty.
- Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $2.50 / $10 for Command A.
- Command A has downloadable open weights; the other is API-only.
Side by side
| Codestral | Command A | |
|---|---|---|
| Provider | Mistral AI | Cohere |
| Noometry Index | 30.6 | 36.5 |
| Released | 2024-05-29 | 2025-03-13 |
| Weights | Proprietary | Open |
| Context window | 256K | 256K |
| Max output | 8K | 8K |
| Input $ / M tokens | $0.30 | $2.50 |
| Output $ / M tokens | $0.90 | $10 |
| Results tracked | 7 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Codestral: 27.3 (#321), Command A: 27.2 (#322)
| Benchmark | Codestral | Command A |
|---|---|---|
| Aider Polyglot | 11.1% | 12% |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1330 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Agentic & Tool Use Not comparable
Codestral: —, Command A: 35.9 (#40)
| Benchmark | Codestral | Command A |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 57.1% |
Reasoning Codestral leads
Codestral: 19.8 (#251), Command A: 18.3 (#283)
| Benchmark | Codestral | Command A |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | 28.8% |
| LMArena Hard Prompts | — | 1326 |
| DTBench | — | 61.3% |
| LMCA | — | 10.3% |
Math Not comparable
Codestral: —, Command A: 36.2 (#171)
| Benchmark | Codestral | Command A |
|---|---|---|
| LMArena Math | — | 1300 |
Knowledge Not comparable
Codestral: —, Command A: 37.1 (#159)
| Benchmark | Codestral | Command A |
|---|---|---|
| Vectara Hallucination Rate | — | 9.3% |
| LMArena Expert | — | 1295 |
Multilingual Not comparable
Codestral: —, Command A: 45.3 (#170)
| Benchmark | Codestral | Command A |
|---|---|---|
| LMArena Non-English | — | 1313 |
| LMArena Chinese | — | 1327 |
| LMArena French | — | 1351 |
| LMArena German | — | 1341 |
| LMArena Japanese | — | 1285 |
| LMArena Korean | — | 1285 |
| LMArena Russian | — | 1314 |
| LMArena Spanish | — | 1347 |
Instruction Following Not comparable
Codestral: —, Command A: 69.1 (#177)
| Benchmark | Codestral | Command A |
|---|---|---|
| LMArena Instruction Following | — | 1309 |
Long Context Not comparable
Codestral: —, Command A: 40.6 (#151)
| Benchmark | Codestral | Command A |
|---|---|---|
| LMArena Longer Query | — | 1334 |
Writing & Preference Not comparable
Codestral: —, Command A: 47.6 (#208)
| Benchmark | Codestral | Command A |
|---|---|---|
| LMArena Text | — | 1331 |
| LMArena Creative Writing | — | 1319 |
| EQ-Bench Creative Writing | — | 1145 |
| LMArena Multi-Turn | — | 1339 |
Frequently asked questions
Is Codestral better than Command A?
Command A is the stronger model overall, scoring 36.5 to 30.6 on the Noometry Index. Codestral costs 9.7× less per token, which makes it the better buy when Command A's lead doesn't matter for your workload.
Which is cheaper, Codestral or Command A?
Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; Command A lists at $2.50 and $10.
Is Codestral or Command A better for coding?
They score almost the same on coding (27.3 vs 27.2); test both on your own repository before choosing.
Which has the bigger context window?
Both accept 256K tokens.
How many benchmarks do Codestral and Command A share?
2 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Command A has 24.