# Claude Sonnet 4.6 vs Mistral Large

> Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 31.9 on the Noometry Index. Mistral Large costs 2.0× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-sonnet-4-6-vs-mistral-large
- Last updated: 2026-10-10
- Shared benchmarks: 29

## Summary

- They share 29 benchmarks with published results for both. Claude Sonnet 4.6 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 Sonnet 4.6 leads 52.9 to 18.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 85.8% for Claude Sonnet 4.6 and 8.5% for Mistral Large.
- Mistral Large is cheaper at $2 / $6 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
- Claude Sonnet 4.6 accepts more context: 1M tokens versus 131K.
- Mistral Large has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Sonnet 4.6 | Mistral Large |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 50.3 | 31.9 |
| Rank | 50 | 263 |
| Context | 1M | 131K |
| Input $/M | $3 | $2 |
| Output $/M | $15 | $6 |
| Weights | Proprietary | Open |

## Coding

- Claude Sonnet 4.6: 46.3 (#67)
- Mistral Large: 34.3 (#240)

| Benchmark | Claude Sonnet 4.6 | Mistral Large |
|---|---|---|
| SciCode | 46.8% | 36.2% |
| LMArena Coding | 1504 | 1277 |
| ALE-Bench | 1,327 | 264.7 |
| SWE-bench Verified | 75.2% | — |
| DeepSWE | 29.9% | — |
| FrontierCode | 24.3% | — |
| LMArena WebDev | 1522 | — |
| WeirdML | 66.1% | — |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |

## Agentic & Tool Use

- Claude Sonnet 4.6: 39.1 (#28)
- Mistral Large: 28.6 (#89)

| Benchmark | Claude Sonnet 4.6 | Mistral Large |
|---|---|---|
| Terminal-Bench | 53.4% | — |
| APEX-Agents | 43% | — |
| Berkeley Function Calling Leaderboard | — | 38.4% |
| OSWorld 2.0 | 9.3% | — |
| DeepResearch Bench | 54.9% | — |
| OSWorld | 72.1% | — |
| ExploitBench | 23.6% | — |
| GBAEval | 48.8% | — |
| GDP.pdf | 18% | — |
| LMArena Search | 1221 | — |
| Vending-Bench 2 | 7,204 | — |

## Reasoning

- Claude Sonnet 4.6: 46.1 (#45)
- Mistral Large: 15.8 (#310)

| Benchmark | Claude Sonnet 4.6 | Mistral Large |
|---|---|---|
| CritPt | 3.1% | 0% |
| LMArena Hard Prompts | 1484 | 1257 |
| DTBench | 89.9% | 65.1% |
| LMCA | 46.5% | 16.7% |
| Epoch Capabilities Index | 152.24 | 128.52 |
| ForecastBench | 62 | 57.1 |
| ARC-AGI-2 | 60.4% | — |
| SimpleBench | — | 22.5% |
| NYT Connections (extended) | 80.9% | — |
| ARC-AGI-1 | 86.5% | — |
| Chess Puzzles | 13% | — |
| Thematic Generalization | 76.3% | — |
| LiveBench Reasoning | — | 43.5% |
| Mystery Game Puzzles | 16% | — |
| LiveBench Data Analysis | — | 50.1% |
| LiveBench | — | 48.4% |

## Math

- Claude Sonnet 4.6: 52.9 (#49)
- Mistral Large: 18.2 (#291)

| Benchmark | Claude Sonnet 4.6 | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 85.8% | 8.5% |
| LMArena Math | 1462 | 1262 |
| FrontierMath (Feb 2025 set) | 32.4% | 0.3% |
| ProofBench | 45% | — |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath Tier 4 (v1) | 8.3% | — |

## Knowledge

- Claude Sonnet 4.6: 51.7 (#65)
- Mistral Large: 30.1 (#230)

| Benchmark | Claude Sonnet 4.6 | Mistral Large |
|---|---|---|
| GPQA Diamond | 87.4% | 51.3% |
| Vectara Hallucination Rate | 10.6% | 4.5% |
| LMArena Expert | 1500 | 1232 |
| SimpleQA Verified | 35.5% | — |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| GPQA (HELM) | — | 43.5% |
| MMLU | — | 80% |

## Multimodal

- Claude Sonnet 4.6: 38.0 (#68)
- Mistral Large: —

| Benchmark | Claude Sonnet 4.6 | Mistral Large |
|---|---|---|
| LMArena Vision | 1283 | — |
| Blueprint-Bench 2 | 6.7% | — |
| LMArena Document | 1482 | — |

## Multilingual

- Claude Sonnet 4.6: 54.4 (#41)
- Mistral Large: 40.0 (#219)

| Benchmark | Claude Sonnet 4.6 | Mistral Large |
|---|---|---|
| LMArena Non-English | 1440 | 1237 |
| LMArena Chinese | 1491 | 1240 |
| LMArena French | 1465 | 1325 |
| LMArena German | 1428 | 1254 |
| LMArena Japanese | 1420 | 1188 |
| LMArena Korean | 1411 | 1202 |
| LMArena Russian | 1440 | 1257 |
| LMArena Spanish | 1464 | 1268 |

## Instruction Following

- Claude Sonnet 4.6: 77.4 (#25)
- Mistral Large: 67.9 (#191)

| Benchmark | Claude Sonnet 4.6 | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1475 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |

## Long Context

- Claude Sonnet 4.6: 45.3 (#44)
- Mistral Large: 38.3 (#199)

| Benchmark | Claude Sonnet 4.6 | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1479 | 1261 |

## Writing & Preference

- Claude Sonnet 4.6: 70.2 (#22)
- Mistral Large: 40.7 (#242)

| Benchmark | Claude Sonnet 4.6 | Mistral Large |
|---|---|---|
| LMArena Text | 1458 | 1266 |
| LMArena Creative Writing | 1435 | 1243 |
| EQ-Bench Creative Writing | 1810 | 985 |
| LMArena Multi-Turn | 1464 | 1260 |
| Short-Story Creative Writing | — | 69% |
| WildBench | — | 80.1% |
| EQ-Bench 4 | 1207 | — |
| LiveBench Language | — | 39.4% |

## FAQ

### Is Claude Sonnet 4.6 better than Mistral Large?

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 31.9 on the Noometry Index. Mistral Large costs 2.0× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.

### Which is cheaper, Claude Sonnet 4.6 or Mistral Large?

Mistral Large is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; Claude Sonnet 4.6 lists at $3 and $15.

### Is Claude Sonnet 4.6 or Mistral Large better for coding?

Claude Sonnet 4.6 scores higher on coding benchmarks: 46.3 versus 34.3 in the Noometry coding category.

### Which has the bigger context window?

Claude Sonnet 4.6 does, with 1M tokens against 131K.

### How many benchmarks do Claude Sonnet 4.6 and Mistral Large share?

29 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Mistral Large has 51.