# Claude Sonnet 4.6 vs Mistral Small 3

> Claude Sonnet 4.6 is the stronger model overall, scoring 50.1 to 30.9 on the Noometry Index. Mistral Small 3 costs 104× 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-small-3
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 8 categories and Mistral Small 3 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude Sonnet 4.6 leads 70.4 to 32.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 85.8% for Claude Sonnet 4.6 and 6.7% for Mistral Small 3.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
- Claude Sonnet 4.6 accepts more context: 1M tokens versus 33K.
- Mistral Small 3 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Sonnet 4.6 | Mistral Small 3 |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 50.1 | 30.9 |
| Rank | 42 | 268 |
| Context | 1M | 33K |
| Input $/M | $3 | $0.05 |
| Output $/M | $15 | $0.08 |
| Weights | Proprietary | Open |

## Coding

- Claude Sonnet 4.6: 46.0 (#62)
- Mistral Small 3: 36.0 (#203)

| Benchmark | Claude Sonnet 4.6 | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1504 | 1246 |
| SWE-bench Verified | 75.2% | — |
| DeepSWE | 29.9% | — |
| FrontierCode | 24.3% | — |
| LMArena WebDev | 1521 | — |
| SciCode | 46.8% | — |
| WeirdML | 66.1% | — |
| BigCodeBench Instruct | — | 45.3% |
| BigCodeBench Complete | — | 50.4% |
| ALE-Bench | 1,327 | — |

## Agentic & Tool Use

- Claude Sonnet 4.6: 39.1 (#26)
- Mistral Small 3: —

| Benchmark | Claude Sonnet 4.6 | Mistral Small 3 |
|---|---|---|
| Terminal-Bench | 53.4% | — |
| APEX-Agents | 43% | — |
| 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 (#40)
- Mistral Small 3: 18.2 (#269)

| Benchmark | Claude Sonnet 4.6 | Mistral Small 3 |
|---|---|---|
| Chess Puzzles | 13% | 0% |
| LMArena Hard Prompts | 1485 | 1233 |
| Epoch Capabilities Index | 152.25 | 127.06 |
| ARC-AGI-2 | 60.4% | — |
| NYT Connections (extended) | 80.9% | — |
| ARC-AGI-1 | 86.5% | — |
| CritPt | 3.1% | — |
| Thematic Generalization | 76.3% | — |
| Mystery Game Puzzles | 16% | — |
| DTBench | 89.9% | — |
| LMCA | 46.5% | — |
| ForecastBench | 62 | — |

## Math

- Claude Sonnet 4.6: 51.9 (#41)
- Mistral Small 3: 15.3 (#290)

| Benchmark | Claude Sonnet 4.6 | Mistral Small 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 85.8% | 6.7% |
| LMArena Math | 1463 | 1240 |
| ProofBench | 45% | — |
| FrontierMath (Feb 2025 set) | 32.4% | — |
| FrontierMath Tier 4 (v1) | 8.3% | — |

## Knowledge

- Claude Sonnet 4.6: 51.6 (#60)
- Mistral Small 3: 25.0 (#258)

| Benchmark | Claude Sonnet 4.6 | Mistral Small 3 |
|---|---|---|
| GPQA Diamond | 87.4% | 47.3% |
| LMArena Expert | 1500 | 1202 |
| SimpleQA Verified | 35.5% | — |
| Confabulations | — | 25.2% |
| Vectara Hallucination Rate | 10.6% | — |

## Multimodal

- Claude Sonnet 4.6: 38.0 (#61)
- Mistral Small 3: —

| Benchmark | Claude Sonnet 4.6 | Mistral Small 3 |
|---|---|---|
| LMArena Vision | 1283 | — |
| Blueprint-Bench 2 | 6.7% | — |
| LMArena Document | 1482 | — |

## Multilingual

- Claude Sonnet 4.6: 54.6 (#39)
- Mistral Small 3: 37.5 (#231)

| Benchmark | Claude Sonnet 4.6 | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1440 | 1198 |
| LMArena Chinese | 1491 | 1204 |
| LMArena French | 1465 | 1202 |
| LMArena German | 1428 | 1211 |
| LMArena Japanese | 1419 | 1111 |
| LMArena Korean | 1411 | 1188 |
| LMArena Russian | 1440 | 1216 |
| LMArena Spanish | 1465 | — |

## Instruction Following

- Claude Sonnet 4.6: 77.6 (#23)
- Mistral Small 3: 63.9 (#224)

| Benchmark | Claude Sonnet 4.6 | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1476 | 1214 |

## Long Context

- Claude Sonnet 4.6: 45.3 (#40)
- Mistral Small 3: 37.8 (#206)

| Benchmark | Claude Sonnet 4.6 | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1479 | 1246 |

## Writing & Preference

- Claude Sonnet 4.6: 70.4 (#22)
- Mistral Small 3: 32.4 (#275)

| Benchmark | Claude Sonnet 4.6 | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1458 | 1234 |
| LMArena Creative Writing | 1435 | 1195 |
| EQ-Bench Creative Writing | 1810 | 707 |
| LMArena Multi-Turn | 1464 | 1217 |
| EQ-Bench 4 | 1207 | — |

## FAQ

### Is Claude Sonnet 4.6 better than Mistral Small 3?

Claude Sonnet 4.6 is the stronger model overall, scoring 50.1 to 30.9 on the Noometry Index. Mistral Small 3 costs 104× 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 Small 3?

Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Claude Sonnet 4.6 lists at $3 and $15.

### Is Claude Sonnet 4.6 or Mistral Small 3 better for coding?

Claude Sonnet 4.6 scores higher on coding benchmarks: 46.0 versus 36.0 in the Noometry coding category.

### Which has the bigger context window?

Claude Sonnet 4.6 does, with 1M tokens against 33K.

### How many benchmarks do Claude Sonnet 4.6 and Mistral Small 3 share?

21 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Mistral Small 3 has 24.