# Claude 3.7 Sonnet vs Mistral Large

> Claude 3.7 Sonnet is the stronger model overall, scoring 39.4 to 31.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-7-sonnet-vs-mistral-large
- Last updated: 2026-10-10
- Shared benchmarks: 39

## Summary

- They share 39 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 9 categories and Mistral Large in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude 3.7 Sonnet leads 35.7 to 17.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 57.8% for Claude 3.7 Sonnet and 8.5% for Mistral Large.
- Mistral Large has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3.7 Sonnet | Mistral Large |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 39.4 | 31.6 |
| Rank | 154 | 258 |
| Context | — | 131K |
| Input $/M | — | $2 |
| Output $/M | — | $6 |
| Weights | Proprietary | Open |

## Coding

- Claude 3.7 Sonnet: 41.1 (#120)
- Mistral Large: 33.8 (#240)

| Benchmark | Claude 3.7 Sonnet | Mistral Large |
|---|---|---|
| LiveBench Coding | 74.5% | 47.1% |
| LMArena Coding | 1361 | 1277 |
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| SciCode | — | 36.2% |
| GSO | 3.8% | — |
| BigCodeBench Instruct | — | 30% |
| BigCodeBench Complete | — | 38.3% |
| CadEval | 54% | — |
| ALE-Bench | — | 264.7 |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |

## Agentic & Tool Use

- Claude 3.7 Sonnet: 33.9 (#46)
- Mistral Large: 28.4 (#83)

| Benchmark | Claude 3.7 Sonnet | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| METR Time Horizons | 60% | — |

## Reasoning

- Claude 3.7 Sonnet: 18.7 (#252)
- Mistral Large: 15.4 (#305)

| Benchmark | Claude 3.7 Sonnet | Mistral Large |
|---|---|---|
| SimpleBench | 46.4% | 22.5% |
| LiveBench Reasoning | 87.8% | 43.5% |
| LMArena Hard Prompts | 1333 | 1257 |
| LiveBench Data Analysis | 74% | 50.1% |
| Epoch Capabilities Index | 141.16 | 128.52 |
| ForecastBench | 61.8 | 57.1 |
| LiveBench | 76.1% | 48.4% |
| ARC-AGI-2 | 0.9% | — |
| ARC-AGI-1 | 28.6% | — |
| CritPt | — | 0% |
| EnigmaEval | 4.2% | — |
| DTBench | — | 65.1% |
| LMCA | — | 16.7% |

## Math

- Claude 3.7 Sonnet: 35.7 (#137)
- Mistral Large: 17.1 (#285)

| Benchmark | Claude 3.7 Sonnet | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 8.5% |
| Omni-MATH | 33% | 28.1% |
| LiveBench Math | 79% | 42.5% |
| LMArena Math | 1336 | 1262 |
| MATH Level 5 | 91.2% | 50.3% |
| FrontierMath (Feb 2025 set) | 4.1% | 0.3% |

## Knowledge

- Claude 3.7 Sonnet: 39.7 (#117)
- Mistral Large: 30.0 (#224)

| Benchmark | Claude 3.7 Sonnet | Mistral Large |
|---|---|---|
| GPQA Diamond | 79.7% | 51.3% |
| MMLU-Pro | 78.4% | 59.9% |
| Confabulations | 14.7% | 21.4% |
| GPQA (HELM) | 60.8% | 43.5% |
| LMArena Expert | 1321 | 1232 |
| Humanity's Last Exam | 8% | — |
| Vectara Hallucination Rate | — | 4.5% |
| MMLU | — | 80% |

## Multimodal

- Claude 3.7 Sonnet: 33.1 (#90)
- Mistral Large: —

| Benchmark | Claude 3.7 Sonnet | Mistral Large |
|---|---|---|
| LMArena Vision | 1169 | — |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |

## Multilingual

- Claude 3.7 Sonnet: 44.3 (#174)
- Mistral Large: 40.1 (#214)

| Benchmark | Claude 3.7 Sonnet | Mistral Large |
|---|---|---|
| LMArena Non-English | 1296 | 1237 |
| LMArena Chinese | 1299 | 1240 |
| LMArena French | 1302 | 1324 |
| LMArena German | 1301 | 1254 |
| LMArena Japanese | 1268 | 1187 |
| LMArena Korean | 1249 | 1202 |
| LMArena Russian | 1311 | 1257 |
| LMArena Spanish | 1299 | 1268 |

## Instruction Following

- Claude 3.7 Sonnet: 73.1 (#120)
- Mistral Large: 68.1 (#186)

| Benchmark | Claude 3.7 Sonnet | Mistral Large |
|---|---|---|
| LiveBench Instruction Following | 81.3% | 67.9% |
| IFEval | 83.4% | 87.7% |
| LMArena Instruction Following | 1352 | 1249 |

## Long Context

- Claude 3.7 Sonnet: 50.2 (#10)
- Mistral Large: 38.3 (#194)

| Benchmark | Claude 3.7 Sonnet | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1373 | 1262 |
| Fiction.LiveBench | 83.3% | — |

## Writing & Preference

- Claude 3.7 Sonnet: 54.6 (#145)
- Mistral Large: 40.9 (#237)

| Benchmark | Claude 3.7 Sonnet | Mistral Large |
|---|---|---|
| LMArena Text | 1314 | 1266 |
| LMArena Creative Writing | 1332 | 1243 |
| Short-Story Creative Writing | 81.1% | 69% |
| EQ-Bench Creative Writing | 1412 | 985 |
| WildBench | 81.4% | 80.1% |
| LMArena Multi-Turn | 1339 | 1260 |
| LiveBench Language | 59.9% | 39.4% |

## FAQ

### Is Claude 3.7 Sonnet better than Mistral Large?

Claude 3.7 Sonnet is the stronger model overall, scoring 39.4 to 31.6 on the Noometry Index.

### Is Claude 3.7 Sonnet or Mistral Large better for coding?

Claude 3.7 Sonnet scores higher on coding benchmarks: 41.1 versus 33.8 in the Noometry coding category.

### How many benchmarks do Claude 3.7 Sonnet and Mistral Large share?

39 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Mistral Large has 51.