Model comparison
Claude 3 Haiku vs Codestral
Codestral is the stronger model overall, scoring 30.6 to 25.9 on the Noometry Index.
Last verified . 5 shared benchmarks.
Mistral AISummary
- They share 5 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Codestral in 2 categories; one gap is clear of the uncertainty.
- The widest gap is in reasoning, where Codestral leads 19.8 to 16.3.
Side by side
| Claude 3 Haiku | Codestral | |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 25.9 | 30.6 |
| Released | 2024-03-07 | 2024-05-29 |
| Weights | Proprietary | Proprietary |
| Context window | — | 256K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $0.90 |
| Results tracked | 37 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude 3 Haiku: 26.4 (#325), Codestral: 27.3 (#321)
| Benchmark | Claude 3 Haiku | Codestral |
|---|---|---|
| BigCodeBench Instruct | 39.4% | 41.8% |
| BigCodeBench Complete | 50.1% | 52.5% |
| HumanEval+ | 68.9% | 73.8% |
| MBPP+ | 68.8% | 61.9% |
| Aider Polyglot | — | 11.1% |
| WeirdML | 9.8% | — |
| LMArena Coding | 1199 | — |
| CadEval | 12% | — |
| ALE-Bench | — | 137.78 |
Reasoning Codestral leads
Claude 3 Haiku: 16.3 (#307), Codestral: 19.8 (#251)
| Benchmark | Claude 3 Haiku | Codestral |
|---|---|---|
| Kagi LLM Benchmark | 34.2% | 32.5% |
| LMArena Hard Prompts | 1174 | — |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.35 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math Not comparable
Claude 3 Haiku: 9.8 (#319), Codestral: —
| Benchmark | Claude 3 Haiku | Codestral |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| LMArena Math | 1188 | — |
| MATH Level 5 | 14.9% | — |
Knowledge Not comparable
Claude 3 Haiku: 17.3 (#285), Codestral: —
| Benchmark | Claude 3 Haiku | Codestral |
|---|---|---|
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| LMArena Expert | 1148 | — |
| MMLU | 73.8% | — |
Multimodal Not comparable
Claude 3 Haiku: 23.6 (#128), Codestral: —
| Benchmark | Claude 3 Haiku | Codestral |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Not comparable
Claude 3 Haiku: 36.0 (#243), Codestral: —
| Benchmark | Claude 3 Haiku | Codestral |
|---|---|---|
| LMArena Non-English | 1178 | — |
| LMArena Chinese | 1155 | — |
| LMArena French | 1195 | — |
| LMArena German | 1174 | — |
| LMArena Japanese | 1102 | — |
| LMArena Korean | 1109 | — |
| LMArena Russian | 1204 | — |
| LMArena Spanish | 1166 | — |
Instruction Following Not comparable
Claude 3 Haiku: 61.3 (#247), Codestral: —
| Benchmark | Claude 3 Haiku | Codestral |
|---|---|---|
| LMArena Instruction Following | 1173 | — |
Long Context Not comparable
Claude 3 Haiku: 36.1 (#237), Codestral: —
| Benchmark | Claude 3 Haiku | Codestral |
|---|---|---|
| LMArena Longer Query | 1190 | — |
Writing & Preference Not comparable
Claude 3 Haiku: 29.7 (#291), Codestral: —
| Benchmark | Claude 3 Haiku | Codestral |
|---|---|---|
| LMArena Text | 1195 | — |
| LMArena Creative Writing | 1157 | — |
| EQ-Bench Creative Writing | 717 | — |
| LMArena Multi-Turn | 1190 | — |
Frequently asked questions
Is Claude 3 Haiku better than Codestral?
Codestral is the stronger model overall, scoring 30.6 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or Codestral better for coding?
They score almost the same on coding (26.4 vs 27.3); test both on your own repository before choosing.
How many benchmarks do Claude 3 Haiku and Codestral share?
5 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Codestral has 7.