Model comparison
Codestral vs Mistral
Codestral and Mistral score almost the same on the Noometry Index (30.6 vs 29.9), so choose on price, context window or the category you care about most.
Last verified . 0 shared benchmarks.
Mistral AISummary
- The widest gap is in coding, where Mistral leads 33.8 to 27.3.
Side by side
| Codestral | Mistral | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 30.6 | 29.9 |
| Released | 2024-05-29 | — |
| Weights | Proprietary | Proprietary |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $0.90 | — |
| Results tracked | 7 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral leads
Codestral: 27.3 (#321), Mistral: 33.8 (#250)
| Benchmark | Codestral | Mistral |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1162 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning Mistral leads
Codestral: 19.8 (#251), Mistral: 22.2 (#200)
| Benchmark | Codestral | Mistral |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| LMArena Hard Prompts | — | 1149 |
Math Not comparable
Codestral: —, Mistral: 22.3 (#278)
| Benchmark | Codestral | Mistral |
|---|---|---|
| Omni-MATH | — | 7.2% |
| LMArena Math | — | 1180 |
Knowledge Not comparable
Codestral: —, Mistral: 16.6 (#288)
| Benchmark | Codestral | Mistral |
|---|---|---|
| MMLU-Pro | — | 27.7% |
| GPQA (HELM) | — | 30.3% |
| LMArena Expert | — | 1125 |
Multilingual Not comparable
Codestral: —, Mistral: 32.8 (#254)
| Benchmark | Codestral | Mistral |
|---|---|---|
| LMArena Non-English | — | 1129 |
| LMArena Chinese | — | 1109 |
| LMArena French | — | 1180 |
| LMArena German | — | 1155 |
| LMArena Japanese | — | 1013 |
| LMArena Korean | — | 1032 |
| LMArena Russian | — | 1168 |
| LMArena Spanish | — | 1143 |
Instruction Following Not comparable
Codestral: —, Mistral: 52.6 (#288)
| Benchmark | Codestral | Mistral |
|---|---|---|
| IFEval | — | 56.8% |
| LMArena Instruction Following | — | 1152 |
Long Context Not comparable
Codestral: —, Mistral: 35.0 (#245)
| Benchmark | Codestral | Mistral |
|---|---|---|
| LMArena Longer Query | — | 1153 |
Writing & Preference Not comparable
Codestral: —, Mistral: 37.0 (#260)
| Benchmark | Codestral | Mistral |
|---|---|---|
| LMArena Text | — | 1165 |
| LMArena Creative Writing | — | 1158 |
| WildBench | — | 66% |
| LMArena Multi-Turn | — | 1147 |
Frequently asked questions
Is Codestral better than Mistral?
Codestral and Mistral score almost the same on the Noometry Index (30.6 vs 29.9), so choose on price, context window or the category you care about most.
Is Codestral or Mistral better for coding?
Mistral scores higher on coding benchmarks: 33.8 versus 27.3 in the Noometry coding category.
How many benchmarks do Codestral and Mistral share?
0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Mistral has 22.