# Claude 3 Sonnet vs Mistral Medium

> Mistral Medium is the stronger model overall, scoring 36.0 to 28.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-sonnet-vs-mistral-medium
- Last updated: 2026-10-10
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and Mistral Medium in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium leads 60.2 to 42.3.
- The biggest single-benchmark swing is MATH Level 5: 18.2% for Claude 3 Sonnet and 81.6% for Mistral Medium.
- Mistral Medium has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Sonnet | Mistral Medium |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 28.8 | 36.0 |
| Rank | 311 | 211 |
| Context | — | 262K |
| Input $/M | — | $1.50 |
| Output $/M | — | $7.50 |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Sonnet: 29.2 (#296)
- Mistral Medium: 33.8 (#241)

| Benchmark | Claude 3 Sonnet | Mistral Medium |
|---|---|---|
| WeirdML | 10.2% | 43.7% |
| LMArena Coding | 1223 | 1434 |
| FrontierCode | — | 8% |
| SciCode | — | 40.2% |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| ALE-Bench | — | 763.98 |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |

## Agentic & Tool Use

- Claude 3 Sonnet: —
- Mistral Medium: 28.1 (#84)

| Benchmark | Claude 3 Sonnet | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |

## Reasoning

- Claude 3 Sonnet: 19.7 (#232)
- Mistral Medium: 23.3 (#165)

| Benchmark | Claude 3 Sonnet | Mistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1426 |
| DTBench | 53.6% | 75.5% |
| Kagi LLM Benchmark | — | 50% |
| CritPt | — | 0% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 120.69 | — |
| WinoGrande | 75.1% | — |

## Math

- Claude 3 Sonnet: 10.0 (#305)
- Mistral Medium: 27.2 (#238)

| Benchmark | Claude 3 Sonnet | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 32.2% |
| LMArena Math | 1213 | 1409 |
| MATH Level 5 | 18.2% | 81.6% |
| ProofBench | — | 9% |
| FrontierMath (Feb 2025 set) | — | 0.3% |

## Knowledge

- Claude 3 Sonnet: 21.1 (#271)
- Mistral Medium: 24.9 (#260)

| Benchmark | Claude 3 Sonnet | Mistral Medium |
|---|---|---|
| GPQA Diamond | 40.6% | 59.5% |
| LMArena Expert | 1173 | 1408 |
| Humanity's Last Exam | — | 4.5% |
| Vectara Hallucination Rate | — | 22.7% |
| MMLU | 75.9% | — |

## Multimodal

- Claude 3 Sonnet: 24.7 (#120)
- Mistral Medium: 34.6 (#82)

| Benchmark | Claude 3 Sonnet | Mistral Medium |
|---|---|---|
| LMArena Vision | 984 | 1172 |

## Multilingual

- Claude 3 Sonnet: 38.0 (#229)
- Mistral Medium: 52.3 (#86)

| Benchmark | Claude 3 Sonnet | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1205 | 1408 |
| LMArena Chinese | 1188 | 1448 |
| LMArena French | 1228 | 1460 |
| LMArena German | 1204 | 1433 |
| LMArena Japanese | 1131 | 1378 |
| LMArena Korean | 1128 | 1382 |
| LMArena Russian | 1227 | 1411 |
| LMArena Spanish | 1204 | 1433 |

## Instruction Following

- Claude 3 Sonnet: 63.1 (#230)
- Mistral Medium: 73.9 (#111)

| Benchmark | Claude 3 Sonnet | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1200 | 1398 |

## Long Context

- Claude 3 Sonnet: 36.7 (#223)
- Mistral Medium: 42.9 (#108)

| Benchmark | Claude 3 Sonnet | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1211 | 1406 |

## Writing & Preference

- Claude 3 Sonnet: 42.3 (#233)
- Mistral Medium: 60.2 (#97)

| Benchmark | Claude 3 Sonnet | Mistral Medium |
|---|---|---|
| LMArena Text | 1218 | 1424 |
| LMArena Creative Writing | 1186 | 1391 |
| LMArena Multi-Turn | 1227 | 1418 |
| Short-Story Creative Writing | — | 77.3% |

## FAQ

### Is Claude 3 Sonnet better than Mistral Medium?

Mistral Medium is the stronger model overall, scoring 36.0 to 28.8 on the Noometry Index.

### Is Claude 3 Sonnet or Mistral Medium better for coding?

Mistral Medium scores higher on coding benchmarks: 33.8 versus 29.2 in the Noometry coding category.

### How many benchmarks do Claude 3 Sonnet and Mistral Medium share?

23 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Mistral Medium has 36.