Model comparison
Claude 3.7 Sonnet vs Kimi K2 (Jul 2025)
Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 39.5 on the Noometry Index.
Last verified . 34 shared benchmarks.
Summary
- They share 34 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 4 categories and Kimi K2 (Jul 2025) in 5 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in long context, where Claude 3.7 Sonnet leads 50.3 to 41.2.
- The biggest single-benchmark swing is Omni-MATH: 33% for Claude 3.7 Sonnet and 65.4% for Kimi K2 (Jul 2025).
- Kimi K2 (Jul 2025) has downloadable open weights; the other is API-only.
Side by side
| Claude 3.7 Sonnet | Kimi K2 (Jul 2025) | |
|---|---|---|
| Provider | Anthropic | Moonshot AI |
| Noometry Index | 39.5 | 41.2 |
| Released | 2025-02-24 | 2025-07-12 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.57 |
| Output $ / M tokens | — | $2.30 |
| Results tracked | 58 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 (Jul 2025) leads
Claude 3.7 Sonnet: 40.6 (#136), Kimi K2 (Jul 2025): 42.4 (#102)
| Benchmark | Claude 3.7 Sonnet | Kimi K2 (Jul 2025) |
|---|---|---|
| SWE-bench Verified (bash only) | 52.8% | 63.4% |
| Aider Polyglot | 64.9% | 59.1% |
| GSO | 3.8% | 4.9% |
| LMArena Coding | 1361 | 1399 |
| SWE-bench Verified | 61% | — |
| WeirdML | — | 42.8% |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
| ALE-Bench | — | 597.5 |
Agentic & Tool Use Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 34.1 (#50), Kimi K2 (Jul 2025): 32.4 (#64)
| Benchmark | Claude 3.7 Sonnet | Kimi K2 (Jul 2025) |
|---|---|---|
| METR Time Horizons | 60% | 59.2% |
| Terminal-Bench | — | 35.7% |
| Berkeley Function Calling Leaderboard | — | 59.1% |
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
Reasoning Kimi K2 (Jul 2025) leads
Claude 3.7 Sonnet: 18.6 (#277), Kimi K2 (Jul 2025): 23.3 (#179)
| Benchmark | Claude 3.7 Sonnet | Kimi K2 (Jul 2025) |
|---|---|---|
| SimpleBench | 46.4% | 26.3% |
| LMArena Hard Prompts | 1333 | 1384 |
| Epoch Capabilities Index | 141.16 | 146.01 |
| ForecastBench | 61.8 | 60.2 |
| ARC-AGI-2 | 0.9% | — |
| Kagi LLM Benchmark | — | 64.4% |
| ARC-AGI-1 | 28.6% | — |
| EnigmaEval | 4.2% | — |
| LiveBench Reasoning | 87.8% | — |
| LiveBench Data Analysis | 74% | — |
| LiveBench | 76.1% | — |
Math Kimi K2 (Jul 2025) leads
Claude 3.7 Sonnet: 37.5 (#153), Kimi K2 (Jul 2025): 42.7 (#83)
| Benchmark | Claude 3.7 Sonnet | Kimi K2 (Jul 2025) |
|---|---|---|
| Omni-MATH | 33% | 65.4% |
| LMArena Math | 1337 | 1397 |
| FrontierMath (Feb 2025 set) | 4.1% | 21.4% |
| OTIS Mock AIME 2024-2025 | 57.8% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 39.8 (#130), Kimi K2 (Jul 2025): 37.3 (#157)
| Benchmark | Claude 3.7 Sonnet | Kimi K2 (Jul 2025) |
|---|---|---|
| MMLU-Pro | 78.4% | 81.9% |
| Confabulations | 14.7% | 20.4% |
| GPQA (HELM) | 60.8% | 65.3% |
| LMArena Expert | 1321 | 1365 |
| GPQA Diamond | 79.7% | — |
| Humanity's Last Exam | 8% | — |
| Vectara Hallucination Rate | — | 17.9% |
Multimodal Not comparable
Claude 3.7 Sonnet: 33.7 (#95), Kimi K2 (Jul 2025): —
| Benchmark | Claude 3.7 Sonnet | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Vision | 1169 | — |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |
Multilingual Kimi K2 (Jul 2025) leads
Claude 3.7 Sonnet: 44.1 (#179), Kimi K2 (Jul 2025): 49.6 (#130)
| Benchmark | Claude 3.7 Sonnet | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | 1296 | 1372 |
| LMArena Chinese | 1299 | 1415 |
| LMArena French | 1303 | 1379 |
| LMArena German | 1301 | 1387 |
| LMArena Japanese | 1267 | 1349 |
| LMArena Korean | 1249 | 1325 |
| LMArena Russian | 1311 | 1385 |
| LMArena Spanish | 1298 | 1386 |
Instruction Following Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 72.9 (#125), Kimi K2 (Jul 2025): 71.1 (#156)
| Benchmark | Claude 3.7 Sonnet | Kimi K2 (Jul 2025) |
|---|---|---|
| IFEval | 83.4% | 85% |
| LMArena Instruction Following | 1352 | 1348 |
| LiveBench Instruction Following | 81.3% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.3 (#10), Kimi K2 (Jul 2025): 41.2 (#145)
| Benchmark | Claude 3.7 Sonnet | Kimi K2 (Jul 2025) |
|---|---|---|
| Fiction.LiveBench | 83.3% | 66.7% |
| LMArena Longer Query | 1373 | 1353 |
| CL-bench | — | 17.6% |
Writing & Preference Kimi K2 (Jul 2025) leads
Claude 3.7 Sonnet: 54.4 (#150), Kimi K2 (Jul 2025): 62.3 (#78)
| Benchmark | Claude 3.7 Sonnet | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | 1314 | 1380 |
| LMArena Creative Writing | 1332 | 1350 |
| Short-Story Creative Writing | 81.1% | 85.6% |
| EQ-Bench Creative Writing | 1412 | 1666 |
| WildBench | 81.4% | 86.2% |
| LMArena Multi-Turn | 1339 | 1371 |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than Kimi K2 (Jul 2025)?
Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 39.5 on the Noometry Index.
Is Claude 3.7 Sonnet or Kimi K2 (Jul 2025) better for coding?
Kimi K2 (Jul 2025) scores higher on coding benchmarks: 42.4 versus 40.6 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and Kimi K2 (Jul 2025) share?
34 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Kimi K2 (Jul 2025) has 42.