# Claude Sonnet 4.5 vs Mistral Small

> Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 33.4 on the Noometry Index. Mistral Small costs 23× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-sonnet-4-5-vs-mistral-small
- Last updated: 2026-10-11
- Shared benchmarks: 28

## Summary

- They share 28 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 10 categories and Mistral Small in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude Sonnet 4.5 leads 48.4 to 31.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Claude Sonnet 4.5 and 5.8% for Mistral Small.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
- Mistral Small accepts more context: 262K tokens versus 200K.
- Mistral Small has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Sonnet 4.5 | Mistral Small |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 44.1 | 33.4 |
| Rank | 81 | 243 |
| Context | 200K | 262K |
| Input $/M | $3 | $0.15 |
| Output $/M | $15 | $0.60 |
| Weights | Proprietary | Open |

## Coding

- Claude Sonnet 4.5: 47.3 (#61)
- Mistral Small: 34.0 (#247)

| Benchmark | Claude Sonnet 4.5 | Mistral Small |
|---|---|---|
| SciCode | 44.7% | 26.5% |
| LMArena Coding | 1489 | 1362 |
| ALE-Bench | 796.15 | 497.62 |
| SWE-bench Verified | 71.3% | — |
| SWE-bench Verified (bash only) | 71.4% | — |
| LMArena WebDev | 1393 | — |
| SWE-bench Multilingual | 67% | — |
| GSO | 14.7% | — |
| WeirdML | 47.7% | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
| AlgoTune | 1.52 | — |

## Agentic & Tool Use

- Claude Sonnet 4.5: 38.3 (#32)
- Mistral Small: 28.1 (#93)

| Benchmark | Claude Sonnet 4.5 | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | 73.2% | 37.1% |
| Terminal-Bench | 46.5% | — |
| GDPval | 42.5% | — |
| Remote Labor Index | 2.1% | — |
| τ²-bench Airline | 72% | — |
| τ²-bench Banking | 25.3% | — |
| τ²-bench Retail | 72.4% | — |
| τ²-bench Telecom | 84.9% | — |
| Cybench | 60% | — |
| DeepResearch Bench | 52.6% | — |
| OSWorld | 62.9% | — |
| LMArena Search | 1159 | — |
| METR Time Horizons | 67.4% | — |
| Vending-Bench 2 | 3,839 | — |

## Reasoning

- Claude Sonnet 4.5: 26.9 (#125)
- Mistral Small: 19.8 (#250)

| Benchmark | Claude Sonnet 4.5 | Mistral Small |
|---|---|---|
| Kagi LLM Benchmark | 57.9% | 37.8% |
| CritPt | 1.1% | 0% |
| LMArena Hard Prompts | 1462 | 1335 |
| DTBench | 83.2% | 70.9% |
| LMCA | 38.8% | 20.6% |
| ARC-AGI-2 | 13.6% | — |
| SimpleBench | 54.3% | — |
| NYT Connections (extended) | 37.3% | — |
| ARC-AGI-1 | 63.7% | — |
| Chess Puzzles | 12% | — |
| EnigmaEval | 6% | — |
| EBR-Bench | 2.4% | — |
| LiveBench Reasoning | — | 44.8% |
| Mystery Game Puzzles | 17% | — |
| LiveBench Data Analysis | — | 53.7% |
| Epoch Capabilities Index | 146.84 | — |
| ForecastBench | 61.9 | — |
| LiveBench | — | 44% |

## Math

- Claude Sonnet 4.5: 32.3 (#216)
- Mistral Small: 16.4 (#293)

| Benchmark | Claude Sonnet 4.5 | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | 5.8% |
| LMArena Math | 1449 | 1341 |
| MATH Level 5 | 97.7% | 46.8% |
| FrontierMath (Tiers 1-3) | 23.9% | — |
| FrontierMath Tier 4 | 2.4% | — |
| ProofBench | 19% | — |
| Omni-MATH | 55.3% | — |
| LiveBench Math | — | 39.9% |
| FrontierMath (Feb 2025 set) | 15.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |

## Knowledge

- Claude Sonnet 4.5: 48.4 (#76)
- Mistral Small: 31.0 (#222)

| Benchmark | Claude Sonnet 4.5 | Mistral Small |
|---|---|---|
| GPQA Diamond | 82.3% | 47.5% |
| Vectara Hallucination Rate | 12% | 5.1% |
| LMArena Expert | 1482 | 1291 |
| Humanity's Last Exam | 13.7% | — |
| SimpleQA Verified | 30.7% | — |
| MMLU-Pro | 86.9% | — |
| GPQA (HELM) | 68.6% | — |
| MMLU | — | 68.7% |

## Multimodal

- Claude Sonnet 4.5: 34.8 (#89)
- Mistral Small: 33.5 (#96)

| Benchmark | Claude Sonnet 4.5 | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |
| VPCT | 39.8% | — |
| LMArena Document | 1450 | — |

## Multilingual

- Claude Sonnet 4.5: 53.4 (#69)
- Mistral Small: 45.5 (#169)

| Benchmark | Claude Sonnet 4.5 | Mistral Small |
|---|---|---|
| LMArena Non-English | 1425 | 1315 |
| LMArena Chinese | 1459 | 1340 |
| LMArena French | 1458 | 1337 |
| LMArena German | 1427 | 1340 |
| LMArena Japanese | 1390 | 1275 |
| LMArena Korean | 1403 | 1259 |
| LMArena Russian | 1437 | 1324 |
| LMArena Spanish | 1457 | 1346 |

## Instruction Following

- Claude Sonnet 4.5: 75.0 (#78)
- Mistral Small: 66.4 (#209)

| Benchmark | Claude Sonnet 4.5 | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1459 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
| IFEval | 85% | — |

## Long Context

- Claude Sonnet 4.5: 45.2 (#46)
- Mistral Small: 40.4 (#156)

| Benchmark | Claude Sonnet 4.5 | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1476 | 1327 |

## Writing & Preference

- Claude Sonnet 4.5: 66.5 (#34)
- Mistral Small: 52.5 (#171)

| Benchmark | Claude Sonnet 4.5 | Mistral Small |
|---|---|---|
| LMArena Text | 1439 | 1338 |
| LMArena Creative Writing | 1442 | 1305 |
| LMArena Multi-Turn | 1465 | 1344 |
| EQ-Bench Creative Writing | 1678 | — |
| WildBench | 85.4% | — |
| LiveBench Language | — | 30.5% |

## FAQ

### Is Claude Sonnet 4.5 better than Mistral Small?

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 33.4 on the Noometry Index. Mistral Small costs 23× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

### Which is cheaper, Claude Sonnet 4.5 or Mistral Small?

Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.

### Is Claude Sonnet 4.5 or Mistral Small better for coding?

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 34.0 in the Noometry coding category.

### Which has the bigger context window?

Mistral Small does, with 262K tokens against 200K.

### How many benchmarks do Claude Sonnet 4.5 and Mistral Small share?

28 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Mistral Small has 39.