Model comparison
Claude 3 Haiku vs Mistral
Mistral is the stronger model overall, scoring 29.4 to 25.7 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AISummary
- They share 17 benchmarks with published results for both. Claude 3 Haiku scores higher in 4 categories and Mistral in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral leads 20.5 to 9.2.
Side by side
| Claude 3 Haiku | Mistral | |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 25.7 | 29.4 |
| Released | 2024-03-07 | — |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 37 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral leads
Claude 3 Haiku: 26.1 (#320), Mistral: 33.2 (#249)
| Benchmark | Claude 3 Haiku | Mistral |
|---|---|---|
| LMArena Coding | 1199 | 1162 |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Reasoning Mistral leads
Claude 3 Haiku: 15.7 (#303), Mistral: 21.3 (#199)
| Benchmark | Claude 3 Haiku | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1149 |
| Kagi LLM Benchmark | 34.2% | — |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.3 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math Mistral leads
Claude 3 Haiku: 9.2 (#313), Mistral: 20.5 (#275)
| Benchmark | Claude 3 Haiku | Mistral |
|---|---|---|
| LMArena Math | 1188 | 1180 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| Omni-MATH | — | 7.2% |
| MATH Level 5 | 14.9% | — |
Knowledge Claude 3 Haiku leads
Claude 3 Haiku: 17.3 (#280), Mistral: 16.3 (#283)
| Benchmark | Claude 3 Haiku | Mistral |
|---|---|---|
| LMArena Expert | 1148 | 1125 |
| GPQA Diamond | 36.3% | — |
| MMLU-Pro | — | 27.7% |
| Confabulations | 34.2% | — |
| GPQA (HELM) | — | 30.3% |
| MMLU | 73.8% | — |
Multimodal Not comparable
Claude 3 Haiku: 23.1 (#123), Mistral: —
| Benchmark | Claude 3 Haiku | Mistral |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Claude 3 Haiku leads
Claude 3 Haiku: 36.1 (#238), Mistral: 33.0 (#249)
| Benchmark | Claude 3 Haiku | Mistral |
|---|---|---|
| LMArena Non-English | 1178 | 1129 |
| LMArena Chinese | 1155 | 1109 |
| LMArena French | 1194 | 1179 |
| LMArena German | 1174 | 1155 |
| LMArena Japanese | 1102 | 1012 |
| LMArena Korean | 1108 | 1032 |
| LMArena Russian | 1204 | 1168 |
| LMArena Spanish | 1165 | 1143 |
Instruction Following Claude 3 Haiku leads
Claude 3 Haiku: 61.5 (#242), Mistral: 52.9 (#283)
| Benchmark | Claude 3 Haiku | Mistral |
|---|---|---|
| LMArena Instruction Following | 1174 | 1152 |
| IFEval | — | 56.8% |
Long Context Claude 3 Haiku leads
Claude 3 Haiku: 36.1 (#232), Mistral: 35.0 (#240)
| Benchmark | Claude 3 Haiku | Mistral |
|---|---|---|
| LMArena Longer Query | 1191 | 1154 |
Writing & Preference Mistral leads
Claude 3 Haiku: 29.8 (#286), Mistral: 37.2 (#255)
| Benchmark | Claude 3 Haiku | Mistral |
|---|---|---|
| LMArena Text | 1195 | 1165 |
| LMArena Creative Writing | 1157 | 1158 |
| LMArena Multi-Turn | 1190 | 1147 |
| EQ-Bench Creative Writing | 717 | — |
| WildBench | — | 66% |
Frequently asked questions
Is Claude 3 Haiku better than Mistral?
Mistral is the stronger model overall, scoring 29.4 to 25.7 on the Noometry Index.
Is Claude 3 Haiku or Mistral better for coding?
Mistral scores higher on coding benchmarks: 33.2 versus 26.1 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Mistral share?
17 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Mistral has 22.