# Claude Haiku 5.5 vs Mistral Small

> Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 33.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-haiku-5-5-vs-mistral-small
- Last updated: 2026-10-12
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Claude Haiku 5.5 scores higher in 5 categories and Mistral Small in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Haiku 5.5 leads 73.6 to 16.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.9% for Claude Haiku 5.5 and 5.8% for Mistral Small.
- Claude Haiku 5.5 is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.15 / $0.60 for Mistral Small.
- Claude Haiku 5.5 accepts more context: 1M tokens versus 262K.
- Mistral Small has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Haiku 5.5 | Mistral Small |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 49.5 | 33.4 |
| Rank | 52 | 243 |
| Context | 1M | 262K |
| Input $/M | $0.10 | $0.15 |
| Output $/M | $0.50 | $0.60 |
| Weights | Proprietary | Open |

## Coding

- Claude Haiku 5.5: 49.2 (#50)
- Mistral Small: 34.0 (#247)

| Benchmark | Claude Haiku 5.5 | Mistral Small |
|---|---|---|
| LMArena WebDev | 1587 | — |
| SciCode | — | 26.5% |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| LMArena Coding | — | 1362 |
| BigCodeBench Complete | — | 46.6% |
| ALE-Bench | — | 497.62 |

## Agentic & Tool Use

- Claude Haiku 5.5: —
- Mistral Small: 28.1 (#93)

| Benchmark | Claude Haiku 5.5 | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |

## Reasoning

- Claude Haiku 5.5: 35.2 (#69)
- Mistral Small: 19.8 (#250)

| Benchmark | Claude Haiku 5.5 | Mistral Small |
|---|---|---|
| Kagi LLM Benchmark | — | 37.8% |
| NYT Connections (extended) | 65.7% | — |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 44.8% |
| LMArena Hard Prompts | — | 1335 |
| Mystery Game Puzzles | 30% | — |
| DTBench | — | 70.9% |
| LiveBench Data Analysis | — | 53.7% |
| LMCA | — | 20.6% |
| LiveBench | — | 44% |

## Math

- Claude Haiku 5.5: 73.6 (#18)
- Mistral Small: 16.4 (#293)

| Benchmark | Claude Haiku 5.5 | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.9% | 5.8% |
| FrontierMath (Tiers 1-3) | 75.1% | — |
| FrontierMath Tier 4 | 46.3% | — |
| LiveBench Math | — | 39.9% |
| LMArena Math | — | 1341 |
| MATH Level 5 | — | 46.8% |

## Knowledge

- Claude Haiku 5.5: 50.8 (#70)
- Mistral Small: 31.0 (#222)

| Benchmark | Claude Haiku 5.5 | Mistral Small |
|---|---|---|
| GPQA Diamond | 89.6% | 47.5% |
| SimpleQA Verified | 23.8% | — |
| Vectara Hallucination Rate | — | 5.1% |
| LMArena Expert | — | 1291 |
| MMLU | — | 68.7% |

## Multimodal

- Claude Haiku 5.5: 43.7 (#21)
- Mistral Small: 33.5 (#96)

| Benchmark | Claude Haiku 5.5 | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |
| Furniture Assembly | 47.5% | — |

## Multilingual

- Claude Haiku 5.5: —
- Mistral Small: 45.5 (#169)

| Benchmark | Claude Haiku 5.5 | Mistral Small |
|---|---|---|
| LMArena Non-English | — | 1315 |
| LMArena Chinese | — | 1340 |
| LMArena French | — | 1337 |
| LMArena German | — | 1340 |
| LMArena Japanese | — | 1275 |
| LMArena Korean | — | 1259 |
| LMArena Russian | — | 1324 |
| LMArena Spanish | — | 1346 |

## Instruction Following

- Claude Haiku 5.5: —
- Mistral Small: 66.4 (#209)

| Benchmark | Claude Haiku 5.5 | Mistral Small |
|---|---|---|
| LiveBench Instruction Following | — | 63.7% |
| LMArena Instruction Following | — | 1310 |

## Long Context

- Claude Haiku 5.5: —
- Mistral Small: 40.4 (#156)

| Benchmark | Claude Haiku 5.5 | Mistral Small |
|---|---|---|
| LMArena Longer Query | — | 1327 |

## Writing & Preference

- Claude Haiku 5.5: —
- Mistral Small: 52.5 (#171)

| Benchmark | Claude Haiku 5.5 | Mistral Small |
|---|---|---|
| LMArena Text | — | 1338 |
| LMArena Creative Writing | — | 1305 |
| LMArena Multi-Turn | — | 1344 |
| LiveBench Language | — | 30.5% |

## FAQ

### Is Claude Haiku 5.5 better than Mistral Small?

Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 33.4 on the Noometry Index.

### Which is cheaper, Claude Haiku 5.5 or Mistral Small?

Claude Haiku 5.5 is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Mistral Small lists at $0.15 and $0.60.

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

Claude Haiku 5.5 scores higher on coding benchmarks: 49.2 versus 34.0 in the Noometry coding category.

### Which has the bigger context window?

Claude Haiku 5.5 does, with 1M tokens against 262K.

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

2 benchmarks have published results for both models. Claude Haiku 5.5 has 9 scored results on Noometry and Mistral Small has 39.