Model comparison
Codestral vs Mistral Small
Mistral Small is the stronger model overall, scoring 33.1 to 30.1 on the Noometry Index.
Last verified . 4 shared benchmarks.
Mistral AISummary
- They share 4 benchmarks with published results for both. Codestral scores higher in 0 categories and Mistral Small in 2 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where Mistral Small leads 33.5 to 26.9.
- The biggest single-benchmark swing is BigCodeBench Complete: 52.5% for Codestral and 46.6% for Mistral Small.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.30 / $0.90 for Codestral.
Side by side
| Codestral | Mistral Small | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 30.1 | 33.1 |
| Released | 2024-05-29 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 256K | 256K |
| Max output | 4K | 256K |
| Input $ / M tokens | $0.30 | $0.15 |
| Output $ / M tokens | $0.90 | $0.60 |
| Results tracked | 7 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small leads
Codestral: 26.9 (#316), Mistral Small: 33.5 (#242)
| Benchmark | Codestral | Mistral Small |
|---|---|---|
| BigCodeBench Instruct | 41.8% | 36.1% |
| BigCodeBench Complete | 52.5% | 46.6% |
| ALE-Bench | 137.78 | 497.62 |
| Aider Polyglot | 11.1% | — |
| SciCode | — | 26.5% |
| LiveBench Coding | — | 36.2% |
| LMArena Coding | — | 1363 |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Agentic & Tool Use Not comparable
Codestral: —, Mistral Small: 27.9 (#87)
| Benchmark | Codestral | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |
Reasoning Too close to call
Codestral: 19.1 (#244), Mistral Small: 19.3 (#238)
| Benchmark | Codestral | Mistral Small |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | 37.8% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 44.8% |
| LMArena Hard Prompts | — | 1336 |
| DTBench | — | 70.9% |
| LiveBench Data Analysis | — | 53.7% |
| LMCA | — | 20.6% |
| LiveBench | — | 44% |
Math Not comparable
Codestral: —, Mistral Small: 15.4 (#287)
| Benchmark | Codestral | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 5.8% |
| LiveBench Math | — | 39.9% |
| LMArena Math | — | 1341 |
| MATH Level 5 | — | 46.8% |
Knowledge Not comparable
Codestral: —, Mistral Small: 30.9 (#214)
| Benchmark | Codestral | Mistral Small |
|---|---|---|
| GPQA Diamond | — | 47.5% |
| Vectara Hallucination Rate | — | 5.1% |
| LMArena Expert | — | 1293 |
| MMLU | — | 68.7% |
Multimodal Not comparable
Codestral: —, Mistral Small: 32.9 (#91)
| Benchmark | Codestral | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |
Multilingual Not comparable
Codestral: —, Mistral Small: 45.7 (#164)
| Benchmark | Codestral | Mistral Small |
|---|---|---|
| LMArena Non-English | — | 1315 |
| LMArena Chinese | — | 1342 |
| LMArena French | — | 1337 |
| LMArena German | — | 1341 |
| LMArena Japanese | — | 1275 |
| LMArena Korean | — | 1260 |
| LMArena Russian | — | 1324 |
| LMArena Spanish | — | 1346 |
Instruction Following Not comparable
Codestral: —, Mistral Small: 66.6 (#204)
| Benchmark | Codestral | Mistral Small |
|---|---|---|
| LiveBench Instruction Following | — | 63.7% |
| LMArena Instruction Following | — | 1310 |
Long Context Not comparable
Codestral: —, Mistral Small: 40.4 (#151)
| Benchmark | Codestral | Mistral Small |
|---|---|---|
| LMArena Longer Query | — | 1327 |
Writing & Preference Not comparable
Codestral: —, Mistral Small: 52.6 (#165)
| Benchmark | Codestral | Mistral Small |
|---|---|---|
| LMArena Text | — | 1338 |
| LMArena Creative Writing | — | 1304 |
| LMArena Multi-Turn | — | 1344 |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is Codestral better than Mistral Small?
Mistral Small is the stronger model overall, scoring 33.1 to 30.1 on the Noometry Index.
Which is cheaper, Codestral or Mistral Small?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Codestral lists at $0.30 and $0.90.
Is Codestral or Mistral Small better for coding?
Mistral Small scores higher on coding benchmarks: 33.5 versus 26.9 in the Noometry coding category.
Which has the bigger context window?
Both accept 256K tokens.
How many benchmarks do Codestral and Mistral Small share?
4 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Mistral Small has 39.