Model comparison
Claude 3 Haiku vs Mistral Large
Mistral Large is the stronger model overall, scoring 31.9 to 25.9 on the Noometry Index.
Last verified . 31 shared benchmarks.
Mistral AISummary
- They share 31 benchmarks with published results for both. Claude 3 Haiku scores higher in 1 category and Mistral Large in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Large leads 30.1 to 17.3.
- The biggest single-benchmark swing is MATH Level 5: 14.9% for Claude 3 Haiku and 50.3% for Mistral Large.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Haiku | Mistral Large | |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 25.9 | 31.9 |
| Released | 2024-03-07 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 37 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large leads
Claude 3 Haiku: 26.4 (#325), Mistral Large: 34.3 (#240)
| Benchmark | Claude 3 Haiku | Mistral Large |
|---|---|---|
| BigCodeBench Instruct | 39.4% | 30% |
| LMArena Coding | 1199 | 1277 |
| BigCodeBench Complete | 50.1% | 38.3% |
| HumanEval+ | 68.9% | 62.2% |
| MBPP+ | 68.8% | 59.5% |
| SciCode | — | 36.2% |
| WeirdML | 9.8% | — |
| LiveBench Coding | — | 47.1% |
| CadEval | 12% | — |
| ALE-Bench | — | 264.7 |
Agentic & Tool Use Not comparable
Claude 3 Haiku: —, Mistral Large: 28.6 (#89)
| Benchmark | Claude 3 Haiku | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |
Reasoning Too close to call
Claude 3 Haiku: 16.3 (#307), Mistral Large: 15.8 (#310)
| Benchmark | Claude 3 Haiku | Mistral Large |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1257 |
| DTBench | 50.1% | 65.1% |
| LMCA | 8.8% | 16.7% |
| Epoch Capabilities Index | 118.35 | 128.52 |
| ForecastBench | 53.2 | 57.1 |
| SimpleBench | — | 22.5% |
| Kagi LLM Benchmark | 34.2% | — |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 43.5% |
| LiveBench Data Analysis | — | 50.1% |
| LiveBench | — | 48.4% |
| WinoGrande | 74.2% | — |
Math Mistral Large leads
Claude 3 Haiku: 9.8 (#319), Mistral Large: 18.2 (#291)
| Benchmark | Claude 3 Haiku | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | 8.5% |
| LMArena Math | 1188 | 1262 |
| MATH Level 5 | 14.9% | 50.3% |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Mistral Large leads
Claude 3 Haiku: 17.3 (#285), Mistral Large: 30.1 (#230)
| Benchmark | Claude 3 Haiku | Mistral Large |
|---|---|---|
| GPQA Diamond | 36.3% | 51.3% |
| Confabulations | 34.2% | 21.4% |
| LMArena Expert | 1148 | 1232 |
| MMLU | 73.8% | 80% |
| MMLU-Pro | — | 59.9% |
| Vectara Hallucination Rate | — | 4.5% |
| GPQA (HELM) | — | 43.5% |
Multimodal Not comparable
Claude 3 Haiku: 23.6 (#128), Mistral Large: —
| Benchmark | Claude 3 Haiku | Mistral Large |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Mistral Large leads
Claude 3 Haiku: 36.0 (#243), Mistral Large: 40.0 (#219)
| Benchmark | Claude 3 Haiku | Mistral Large |
|---|---|---|
| LMArena Non-English | 1178 | 1237 |
| LMArena Chinese | 1155 | 1240 |
| LMArena French | 1195 | 1325 |
| LMArena German | 1174 | 1254 |
| LMArena Japanese | 1102 | 1188 |
| LMArena Korean | 1109 | 1202 |
| LMArena Russian | 1204 | 1257 |
| LMArena Spanish | 1166 | 1268 |
Instruction Following Mistral Large leads
Claude 3 Haiku: 61.3 (#247), Mistral Large: 67.9 (#191)
| Benchmark | Claude 3 Haiku | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1173 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |
Long Context Mistral Large leads
Claude 3 Haiku: 36.1 (#237), Mistral Large: 38.3 (#199)
| Benchmark | Claude 3 Haiku | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1190 | 1261 |
Writing & Preference Mistral Large leads
Claude 3 Haiku: 29.7 (#291), Mistral Large: 40.7 (#242)
| Benchmark | Claude 3 Haiku | Mistral Large |
|---|---|---|
| LMArena Text | 1195 | 1266 |
| LMArena Creative Writing | 1157 | 1243 |
| EQ-Bench Creative Writing | 717 | 985 |
| LMArena Multi-Turn | 1190 | 1260 |
| Short-Story Creative Writing | — | 69% |
| WildBench | — | 80.1% |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is Claude 3 Haiku better than Mistral Large?
Mistral Large is the stronger model overall, scoring 31.9 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or Mistral Large better for coding?
Mistral Large scores higher on coding benchmarks: 34.3 versus 26.4 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Mistral Large share?
31 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Mistral Large has 51.