# Claude 3.5 Haiku vs Mistral Large

> Mistral Large is the stronger model overall, scoring 31.9 to 29.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-5-haiku-vs-mistral-large
- Last updated: 2026-10-12
- Shared benchmarks: 43

## Summary

- They share 43 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 3 categories and Mistral Large in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Large leads 30.1 to 18.7.
- The biggest single-benchmark swing is BigCodeBench Complete: 59% for Claude 3.5 Haiku and 38.3% for Mistral Large.
- Mistral Large has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3.5 Haiku | Mistral Large |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 29.2 | 31.9 |
| Rank | 315 | 263 |
| Context | — | 131K |
| Input $/M | — | $2 |
| Output $/M | — | $6 |
| Weights | Proprietary | Open |

## Coding

- Claude 3.5 Haiku: 32.9 (#265)
- Mistral Large: 34.3 (#240)

| Benchmark | Claude 3.5 Haiku | Mistral Large |
|---|---|---|
| SciCode | 27.4% | 36.2% |
| BigCodeBench Instruct | 46.1% | 30% |
| LiveBench Coding | 51.4% | 47.1% |
| LMArena Coding | 1286 | 1277 |
| BigCodeBench Complete | 59% | 38.3% |
| Aider Polyglot | 28% | — |
| WeirdML | 30.7% | — |
| CadEval | 32% | — |
| ALE-Bench | — | 264.7 |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |

## Agentic & Tool Use

- Claude 3.5 Haiku: 28.0 (#95)
- Mistral Large: 28.6 (#89)

| Benchmark | Claude 3.5 Haiku | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |
| BALROG | 19.3% | — |

## Reasoning

- Claude 3.5 Haiku: 17.7 (#290)
- Mistral Large: 15.8 (#310)

| Benchmark | Claude 3.5 Haiku | Mistral Large |
|---|---|---|
| CritPt | 0% | 0% |
| LiveBench Reasoning | 28.1% | 43.5% |
| LMArena Hard Prompts | 1251 | 1257 |
| DTBench | 56.7% | 65.1% |
| LiveBench Data Analysis | 48.5% | 50.1% |
| Epoch Capabilities Index | 127.15 | 128.52 |
| LiveBench | 43.5% | 48.4% |
| SimpleBench | — | 22.5% |
| LMCA | — | 16.7% |
| ForecastBench | — | 57.1 |

## Math

- Claude 3.5 Haiku: 14.7 (#300)
- Mistral Large: 18.2 (#291)

| Benchmark | Claude 3.5 Haiku | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 8.5% |
| Omni-MATH | 22.4% | 28.1% |
| LiveBench Math | 35.5% | 42.5% |
| LMArena Math | 1244 | 1262 |
| MATH Level 5 | 46.4% | 50.3% |
| FrontierMath (Feb 2025 set) | 0.3% | 0.3% |

## Knowledge

- Claude 3.5 Haiku: 18.7 (#281)
- Mistral Large: 30.1 (#230)

| Benchmark | Claude 3.5 Haiku | Mistral Large |
|---|---|---|
| GPQA Diamond | 38.1% | 51.3% |
| MMLU-Pro | 60.5% | 59.9% |
| Confabulations | 36.7% | 21.4% |
| GPQA (HELM) | 36.3% | 43.5% |
| LMArena Expert | 1208 | 1232 |
| MMLU | 74.3% | 80% |
| Vectara Hallucination Rate | — | 4.5% |

## Multimodal

- Claude 3.5 Haiku: 26.8 (#117)
- Mistral Large: —

| Benchmark | Claude 3.5 Haiku | Mistral Large |
|---|---|---|
| LMArena Vision | 1092 | — |
| GeoBench | 34% | — |

## Multilingual

- Claude 3.5 Haiku: 40.0 (#218)
- Mistral Large: 40.0 (#219)

| Benchmark | Claude 3.5 Haiku | Mistral Large |
|---|---|---|
| LMArena Non-English | 1238 | 1237 |
| LMArena Chinese | 1229 | 1240 |
| LMArena French | 1264 | 1325 |
| LMArena German | 1237 | 1254 |
| LMArena Japanese | 1175 | 1188 |
| LMArena Korean | 1173 | 1202 |
| LMArena Russian | 1253 | 1257 |
| LMArena Spanish | 1261 | 1268 |

## Instruction Following

- Claude 3.5 Haiku: 62.9 (#234)
- Mistral Large: 67.9 (#191)

| Benchmark | Claude 3.5 Haiku | Mistral Large |
|---|---|---|
| LiveBench Instruction Following | 61.9% | 67.9% |
| IFEval | 79.2% | 87.7% |
| LMArena Instruction Following | 1241 | 1249 |

## Long Context

- Claude 3.5 Haiku: 38.3 (#200)
- Mistral Large: 38.3 (#199)

| Benchmark | Claude 3.5 Haiku | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1261 | 1261 |

## Writing & Preference

- Claude 3.5 Haiku: 42.7 (#234)
- Mistral Large: 40.7 (#242)

| Benchmark | Claude 3.5 Haiku | Mistral Large |
|---|---|---|
| LMArena Text | 1255 | 1266 |
| LMArena Creative Writing | 1233 | 1243 |
| Short-Story Creative Writing | 73.5% | 69% |
| EQ-Bench Creative Writing | 1146 | 985 |
| WildBench | 76% | 80.1% |
| LMArena Multi-Turn | 1265 | 1260 |
| LiveBench Language | 35.4% | 39.4% |

## FAQ

### Is Claude 3.5 Haiku better than Mistral Large?

Mistral Large is the stronger model overall, scoring 31.9 to 29.2 on the Noometry Index.

### Is Claude 3.5 Haiku or Mistral Large better for coding?

Mistral Large scores higher on coding benchmarks: 34.3 versus 32.9 in the Noometry coding category.

### How many benchmarks do Claude 3.5 Haiku and Mistral Large share?

43 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Mistral Large has 51.