# Claude 3.7 Sonnet vs Kimi K2.6

> Kimi K2.6 is the stronger model overall, scoring 47.7 to 39.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-7-sonnet-vs-kimi-k2-6
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 3 categories and Kimi K2.6 in 7 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2.6 leads 40.5 to 18.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 57.8% for Claude 3.7 Sonnet and 96.1% for Kimi K2.6.
- Kimi K2.6 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3.7 Sonnet | Kimi K2.6 |
|---|---|---|
| Provider | Anthropic | Moonshot AI |
| Noometry Index | 39.5 | 47.7 |
| Rank | 164 | 60 |
| Context | — | 262K |
| Input $/M | — | $0.95 |
| Output $/M | — | $4 |
| Weights | Proprietary | Open |

## Coding

- Claude 3.7 Sonnet: 40.6 (#136)
- Kimi K2.6: 50.7 (#43)

| Benchmark | Claude 3.7 Sonnet | Kimi K2.6 |
|---|---|---|
| SWE-bench Verified | 61% | 76.7% |
| LMArena Coding | 1361 | 1488 |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| LMArena WebDev | — | 1509 |
| SciCode | — | 53.5% |
| GSO | 3.8% | — |
| WeirdML | — | 55.9% |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
| ALE-Bench | — | 1,093 |

## Agentic & Tool Use

- Claude 3.7 Sonnet: 34.1 (#50)
- Kimi K2.6: 21.9 (#137)

| Benchmark | Claude 3.7 Sonnet | Kimi K2.6 |
|---|---|---|
| OSWorld 2.0 | — | 4.6% |
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| ExploitBench | — | 18.4% |
| GBAEval | — | 0.9% |
| GDP.pdf | — | 12% |
| METR Time Horizons | 60% | — |
| Vending-Bench 2 | — | 6,205 |

## Reasoning

- Claude 3.7 Sonnet: 18.6 (#277)
- Kimi K2.6: 40.5 (#55)

| Benchmark | Claude 3.7 Sonnet | Kimi K2.6 |
|---|---|---|
| LMArena Hard Prompts | 1333 | 1470 |
| Epoch Capabilities Index | 141.16 | 151.05 |
| ARC-AGI-2 | 0.9% | — |
| SimpleBench | 46.4% | — |
| NYT Connections (extended) | — | 87.2% |
| ARC-AGI-1 | 28.6% | — |
| CritPt | — | 8% |
| Chess Puzzles | — | 26% |
| EnigmaEval | 4.2% | — |
| EBR-Bench | — | 2.4% |
| LiveBench Reasoning | 87.8% | — |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 90.9% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 37.3% |
| ForecastBench | 61.8 | — |
| LiveBench | 76.1% | — |

## Math

- Claude 3.7 Sonnet: 37.5 (#153)
- Kimi K2.6: 57.0 (#41)

| Benchmark | Claude 3.7 Sonnet | Kimi K2.6 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 96.1% |
| LMArena Math | 1337 | 1475 |
| FrontierMath (Feb 2025 set) | 4.1% | 39% |
| FrontierMath (Tiers 1-3) | — | 57.2% |
| FrontierMath Tier 4 | — | 25.6% |
| MathArena Final-Answer Competitions | — | 72.9% |
| ProofBench | — | 16% |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath Tier 4 (v1) | — | 14.6% |

## Knowledge

- Claude 3.7 Sonnet: 39.8 (#130)
- Kimi K2.6: 54.0 (#54)

| Benchmark | Claude 3.7 Sonnet | Kimi K2.6 |
|---|---|---|
| GPQA Diamond | 79.7% | 90.8% |
| LMArena Expert | 1321 | 1491 |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | — | 34.9% |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| Vectara Hallucination Rate | — | 10.8% |
| GPQA (HELM) | 60.8% | — |

## Multimodal

- Claude 3.7 Sonnet: 33.7 (#95)
- Kimi K2.6: 31.6 (#103)

| Benchmark | Claude 3.7 Sonnet | Kimi K2.6 |
|---|---|---|
| LMArena Vision | 1169 | 1283 |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| Blueprint-Bench 2 | — | 3.9% |
| Furniture Assembly | — | 21.7% |
| LMArena Document | — | 1451 |
| SpatialViz-Bench | 33.9% | — |

## Multilingual

- Claude 3.7 Sonnet: 44.1 (#179)
- Kimi K2.6: 54.9 (#37)

| Benchmark | Claude 3.7 Sonnet | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | 1296 | 1446 |
| LMArena Chinese | 1299 | 1521 |
| LMArena French | 1303 | 1471 |
| LMArena German | 1301 | 1450 |
| LMArena Japanese | 1267 | 1443 |
| LMArena Korean | 1249 | 1427 |
| LMArena Russian | 1311 | 1446 |
| LMArena Spanish | 1298 | 1464 |

## Instruction Following

- Claude 3.7 Sonnet: 72.9 (#125)
- Kimi K2.6: 76.3 (#43)

| Benchmark | Claude 3.7 Sonnet | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | 1352 | 1451 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |

## Long Context

- Claude 3.7 Sonnet: 50.3 (#10)
- Kimi K2.6: 44.9 (#52)

| Benchmark | Claude 3.7 Sonnet | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | 1373 | 1468 |
| Fiction.LiveBench | 83.3% | — |

## Writing & Preference

- Claude 3.7 Sonnet: 54.4 (#150)
- Kimi K2.6: 68.5 (#26)

| Benchmark | Claude 3.7 Sonnet | Kimi K2.6 |
|---|---|---|
| LMArena Text | 1314 | 1455 |
| LMArena Creative Writing | 1332 | 1434 |
| EQ-Bench Creative Writing | 1412 | 1725 |
| LMArena Multi-Turn | 1339 | 1453 |
| Short-Story Creative Writing | 81.1% | — |
| WildBench | 81.4% | — |
| EQ-Bench 4 | — | 1202 |
| LiveBench Language | 59.9% | — |

## FAQ

### Is Claude 3.7 Sonnet better than Kimi K2.6?

Kimi K2.6 is the stronger model overall, scoring 47.7 to 39.5 on the Noometry Index.

### Is Claude 3.7 Sonnet or Kimi K2.6 better for coding?

Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 40.6 in the Noometry coding category.

### How many benchmarks do Claude 3.7 Sonnet and Kimi K2.6 share?

24 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Kimi K2.6 has 51.