# Claude 3 Haiku vs Mistral Small

> Mistral Small is the stronger model overall, scoring 33.4 to 25.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-haiku-vs-mistral-small
- Last updated: 2026-10-10
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Mistral Small in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Small leads 52.5 to 29.7.
- The biggest single-benchmark swing is MATH Level 5: 14.9% for Claude 3 Haiku and 46.8% for Mistral Small.
- Mistral Small has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Haiku | Mistral Small |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 25.9 | 33.4 |
| Rank | 340 | 243 |
| Context | — | 262K |
| Input $/M | — | $0.15 |
| Output $/M | — | $0.60 |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Haiku: 26.4 (#325)
- Mistral Small: 34.0 (#247)

| Benchmark | Claude 3 Haiku | Mistral Small |
|---|---|---|
| BigCodeBench Instruct | 39.4% | 36.1% |
| LMArena Coding | 1199 | 1362 |
| BigCodeBench Complete | 50.1% | 46.6% |
| SciCode | — | 26.5% |
| WeirdML | 9.8% | — |
| LiveBench Coding | — | 36.2% |
| CadEval | 12% | — |
| ALE-Bench | — | 497.62 |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |

## Agentic & Tool Use

- Claude 3 Haiku: —
- Mistral Small: 28.1 (#93)

| Benchmark | Claude 3 Haiku | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |

## Reasoning

- Claude 3 Haiku: 16.3 (#307)
- Mistral Small: 19.8 (#250)

| Benchmark | Claude 3 Haiku | Mistral Small |
|---|---|---|
| Kagi LLM Benchmark | 34.2% | 37.8% |
| LMArena Hard Prompts | 1174 | 1335 |
| DTBench | 50.1% | 70.9% |
| LMCA | 8.8% | 20.6% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 44.8% |
| LiveBench Data Analysis | — | 53.7% |
| Epoch Capabilities Index | 118.35 | — |
| ForecastBench | 53.2 | — |
| LiveBench | — | 44% |
| WinoGrande | 74.2% | — |

## Math

- Claude 3 Haiku: 9.8 (#319)
- Mistral Small: 16.4 (#293)

| Benchmark | Claude 3 Haiku | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | 5.8% |
| LMArena Math | 1188 | 1341 |
| MATH Level 5 | 14.9% | 46.8% |
| LiveBench Math | — | 39.9% |

## Knowledge

- Claude 3 Haiku: 17.3 (#285)
- Mistral Small: 31.0 (#222)

| Benchmark | Claude 3 Haiku | Mistral Small |
|---|---|---|
| GPQA Diamond | 36.3% | 47.5% |
| LMArena Expert | 1148 | 1291 |
| MMLU | 73.8% | 68.7% |
| Confabulations | 34.2% | — |
| Vectara Hallucination Rate | — | 5.1% |

## Multimodal

- Claude 3 Haiku: 23.6 (#128)
- Mistral Small: 33.5 (#96)

| Benchmark | Claude 3 Haiku | Mistral Small |
|---|---|---|
| LMArena Vision | 950 | 1142 |
| ScienceQA | 72% | — |

## Multilingual

- Claude 3 Haiku: 36.0 (#243)
- Mistral Small: 45.5 (#169)

| Benchmark | Claude 3 Haiku | Mistral Small |
|---|---|---|
| LMArena Non-English | 1178 | 1315 |
| LMArena Chinese | 1155 | 1340 |
| LMArena French | 1195 | 1337 |
| LMArena German | 1174 | 1340 |
| LMArena Japanese | 1102 | 1275 |
| LMArena Korean | 1109 | 1259 |
| LMArena Russian | 1204 | 1324 |
| LMArena Spanish | 1166 | 1346 |

## Instruction Following

- Claude 3 Haiku: 61.3 (#247)
- Mistral Small: 66.4 (#209)

| Benchmark | Claude 3 Haiku | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1173 | 1310 |
| LiveBench Instruction Following | — | 63.7% |

## Long Context

- Claude 3 Haiku: 36.1 (#237)
- Mistral Small: 40.4 (#156)

| Benchmark | Claude 3 Haiku | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1190 | 1327 |

## Writing & Preference

- Claude 3 Haiku: 29.7 (#291)
- Mistral Small: 52.5 (#171)

| Benchmark | Claude 3 Haiku | Mistral Small |
|---|---|---|
| LMArena Text | 1195 | 1338 |
| LMArena Creative Writing | 1157 | 1305 |
| LMArena Multi-Turn | 1190 | 1344 |
| EQ-Bench Creative Writing | 717 | — |
| LiveBench Language | — | 30.5% |

## FAQ

### Is Claude 3 Haiku better than Mistral Small?

Mistral Small is the stronger model overall, scoring 33.4 to 25.9 on the Noometry Index.

### Is Claude 3 Haiku or Mistral Small better for coding?

Mistral Small scores higher on coding benchmarks: 34.0 versus 26.4 in the Noometry coding category.

### How many benchmarks do Claude 3 Haiku and Mistral Small share?

27 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Mistral Small has 39.