# Claude Haiku 5.5 vs Mistral

> Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 29.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-haiku-5-5-vs-mistral
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where Claude Haiku 5.5 leads 73.6 to 22.3.

## Snapshot

| | Claude Haiku 5.5 | Mistral |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 49.5 | 29.9 |
| Rank | 52 | 303 |
| Context | 1M | — |
| Input $/M | $0.10 | — |
| Output $/M | $0.50 | — |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Haiku 5.5: 49.2 (#50)
- Mistral: 33.8 (#250)

| Benchmark | Claude Haiku 5.5 | Mistral |
|---|---|---|
| LMArena WebDev | 1587 | — |
| LMArena Coding | — | 1162 |

## Reasoning

- Claude Haiku 5.5: 35.2 (#69)
- Mistral: 22.2 (#200)

| Benchmark | Claude Haiku 5.5 | Mistral |
|---|---|---|
| NYT Connections (extended) | 65.7% | — |
| LMArena Hard Prompts | — | 1149 |
| Mystery Game Puzzles | 30% | — |

## Math

- Claude Haiku 5.5: 73.6 (#18)
- Mistral: 22.3 (#278)

| Benchmark | Claude Haiku 5.5 | Mistral |
|---|---|---|
| FrontierMath (Tiers 1-3) | 75.1% | — |
| FrontierMath Tier 4 | 46.3% | — |
| OTIS Mock AIME 2024-2025 | 98.9% | — |
| Omni-MATH | — | 7.2% |
| LMArena Math | — | 1180 |

## Knowledge

- Claude Haiku 5.5: 50.8 (#70)
- Mistral: 16.6 (#288)

| Benchmark | Claude Haiku 5.5 | Mistral |
|---|---|---|
| GPQA Diamond | 89.6% | — |
| SimpleQA Verified | 23.8% | — |
| MMLU-Pro | — | 27.7% |
| GPQA (HELM) | — | 30.3% |
| LMArena Expert | — | 1125 |

## Multimodal

- Claude Haiku 5.5: 43.7 (#21)
- Mistral: —

| Benchmark | Claude Haiku 5.5 | Mistral |
|---|---|---|
| Furniture Assembly | 47.5% | — |

## Multilingual

- Claude Haiku 5.5: —
- Mistral: 32.8 (#254)

| Benchmark | Claude Haiku 5.5 | Mistral |
|---|---|---|
| LMArena Non-English | — | 1129 |
| LMArena Chinese | — | 1109 |
| LMArena French | — | 1180 |
| LMArena German | — | 1155 |
| LMArena Japanese | — | 1013 |
| LMArena Korean | — | 1032 |
| LMArena Russian | — | 1168 |
| LMArena Spanish | — | 1143 |

## Instruction Following

- Claude Haiku 5.5: —
- Mistral: 52.6 (#288)

| Benchmark | Claude Haiku 5.5 | Mistral |
|---|---|---|
| IFEval | — | 56.8% |
| LMArena Instruction Following | — | 1152 |

## Long Context

- Claude Haiku 5.5: —
- Mistral: 35.0 (#245)

| Benchmark | Claude Haiku 5.5 | Mistral |
|---|---|---|
| LMArena Longer Query | — | 1153 |

## Writing & Preference

- Claude Haiku 5.5: —
- Mistral: 37.0 (#260)

| Benchmark | Claude Haiku 5.5 | Mistral |
|---|---|---|
| LMArena Text | — | 1165 |
| LMArena Creative Writing | — | 1158 |
| WildBench | — | 66% |
| LMArena Multi-Turn | — | 1147 |

## FAQ

### Is Claude Haiku 5.5 better than Mistral?

Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 29.9 on the Noometry Index.

### Is Claude Haiku 5.5 or Mistral better for coding?

Claude Haiku 5.5 scores higher on coding benchmarks: 49.2 versus 33.8 in the Noometry coding category.

### How many benchmarks do Claude Haiku 5.5 and Mistral share?

0 benchmarks have published results for both models. Claude Haiku 5.5 has 9 scored results on Noometry and Mistral has 22.