Model comparison
Claude Sonnet 4.5 vs Kimi K2 Thinking Turbo
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 44.1 on the Noometry Index.
Last verified . 21 shared benchmarks.
Summary
- They share 21 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 5 categories and Kimi K2 Thinking Turbo in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2 Thinking Turbo leads 47.4 to 32.3.
- The biggest single-benchmark swing is Chess Puzzles: 12% for Claude Sonnet 4.5 and 20% for Kimi K2 Thinking Turbo.
- Kimi K2 Thinking Turbo has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4.5 | Kimi K2 Thinking Turbo | |
|---|---|---|
| Provider | Anthropic | Moonshot AI |
| Noometry Index | 44.1 | 45.8 |
| Released | 2025-09-29 | 2025-11-06 |
| Weights | Proprietary | Open |
| Context window | 200K | — |
| Max output | 64K | — |
| Input $ / M tokens | $3 | — |
| Output $ / M tokens | $15 | — |
| Results tracked | 73 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 47.3 (#61), Kimi K2 Thinking Turbo: 38.4 (#178)
| Benchmark | Claude Sonnet 4.5 | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena WebDev | 1393 | 1322 |
| LMArena Coding | 1489 | 1454 |
| SWE-bench Verified | 71.3% | — |
| SWE-bench Verified (bash only) | 71.4% | — |
| SWE-bench Multilingual | 67% | — |
| SciCode | 44.7% | — |
| GSO | 14.7% | — |
| WeirdML | 47.7% | — |
| ALE-Bench | 796.15 | — |
| AlgoTune | 1.52 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 4.5: 38.3 (#32), Kimi K2 Thinking Turbo: —
| Benchmark | Claude Sonnet 4.5 | Kimi K2 Thinking Turbo |
|---|---|---|
| Terminal-Bench | 46.5% | — |
| Berkeley Function Calling Leaderboard | 73.2% | — |
| GDPval | 42.5% | — |
| Remote Labor Index | 2.1% | — |
| τ²-bench Airline | 72% | — |
| τ²-bench Banking | 25.3% | — |
| τ²-bench Retail | 72.4% | — |
| τ²-bench Telecom | 84.9% | — |
| Cybench | 60% | — |
| DeepResearch Bench | 52.6% | — |
| OSWorld | 62.9% | — |
| LMArena Search | 1159 | — |
| METR Time Horizons | 67.4% | — |
| Vending-Bench 2 | 3,839 | — |
Reasoning Kimi K2 Thinking Turbo leads
Claude Sonnet 4.5: 26.9 (#125), Kimi K2 Thinking Turbo: 32.5 (#75)
| Benchmark | Claude Sonnet 4.5 | Kimi K2 Thinking Turbo |
|---|---|---|
| Chess Puzzles | 12% | 20% |
| LMArena Hard Prompts | 1462 | 1428 |
| ARC-AGI-2 | 13.6% | — |
| SimpleBench | 54.3% | — |
| Kagi LLM Benchmark | 57.9% | — |
| NYT Connections (extended) | 37.3% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 1.1% | — |
| EnigmaEval | 6% | — |
| EBR-Bench | 2.4% | — |
| Mystery Game Puzzles | 17% | — |
| DTBench | 83.2% | — |
| LMCA | 38.8% | — |
| Epoch Capabilities Index | 146.84 | — |
| ForecastBench | 61.9 | — |
Math Kimi K2 Thinking Turbo leads
Claude Sonnet 4.5: 32.3 (#216), Kimi K2 Thinking Turbo: 47.4 (#68)
| Benchmark | Claude Sonnet 4.5 | Kimi K2 Thinking Turbo |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | 83.1% |
| LMArena Math | 1449 | 1429 |
| FrontierMath (Tiers 1-3) | 23.9% | — |
| FrontierMath Tier 4 | 2.4% | — |
| ProofBench | 19% | — |
| Omni-MATH | 55.3% | — |
| MATH Level 5 | 97.7% | — |
| FrontierMath (Feb 2025 set) | 15.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Kimi K2 Thinking Turbo leads
Claude Sonnet 4.5: 48.4 (#76), Kimi K2 Thinking Turbo: 50.9 (#69)
| Benchmark | Claude Sonnet 4.5 | Kimi K2 Thinking Turbo |
|---|---|---|
| GPQA Diamond | 82.3% | 84.2% |
| LMArena Expert | 1482 | 1439 |
| Humanity's Last Exam | 13.7% | — |
| SimpleQA Verified | 30.7% | — |
| MMLU-Pro | 86.9% | — |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 68.6% | — |
Multimodal Not comparable
Claude Sonnet 4.5: 34.8 (#89), Kimi K2 Thinking Turbo: —
| Benchmark | Claude Sonnet 4.5 | Kimi K2 Thinking Turbo |
|---|---|---|
| VPCT | 39.8% | — |
| LMArena Document | 1450 | — |
Multilingual Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 53.4 (#69), Kimi K2 Thinking Turbo: 51.4 (#109)
| Benchmark | Claude Sonnet 4.5 | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Non-English | 1425 | 1398 |
| LMArena Chinese | 1459 | 1456 |
| LMArena French | 1458 | 1425 |
| LMArena German | 1427 | 1390 |
| LMArena Japanese | 1390 | 1357 |
| LMArena Korean | 1403 | 1330 |
| LMArena Russian | 1437 | 1391 |
| LMArena Spanish | 1457 | 1406 |
Instruction Following Too close to call
Claude Sonnet 4.5: 75.0 (#78), Kimi K2 Thinking Turbo: 74.0 (#109)
| Benchmark | Claude Sonnet 4.5 | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Instruction Following | 1459 | 1403 |
| IFEval | 85% | — |
Long Context Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 45.2 (#46), Kimi K2 Thinking Turbo: 43.2 (#102)
| Benchmark | Claude Sonnet 4.5 | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Longer Query | 1476 | 1415 |
Writing & Preference Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 66.5 (#34), Kimi K2 Thinking Turbo: 60.0 (#104)
| Benchmark | Claude Sonnet 4.5 | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Text | 1439 | 1415 |
| LMArena Creative Writing | 1442 | 1374 |
| LMArena Multi-Turn | 1465 | 1414 |
| EQ-Bench Creative Writing | 1678 | — |
| WildBench | 85.4% | — |
Frequently asked questions
Is Claude Sonnet 4.5 better than Kimi K2 Thinking Turbo?
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 44.1 on the Noometry Index.
Is Claude Sonnet 4.5 or Kimi K2 Thinking Turbo better for coding?
Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 38.4 in the Noometry coding category.
How many benchmarks do Claude Sonnet 4.5 and Kimi K2 Thinking Turbo share?
21 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Kimi K2 Thinking Turbo has 21.