Model comparison
Claude Sonnet 4 vs Kimi K2.5
Kimi K2.5 is the stronger model overall, scoring 48.1 to 40.8 on the Noometry Index.
Last verified . 38 shared benchmarks.
Summary
- They share 38 benchmarks with published results for both. Claude Sonnet 4 scores higher in 1 category and Kimi K2.5 in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in long context, where Kimi K2.5 leads 52.1 to 33.7.
- The biggest single-benchmark swing is Fiction.LiveBench: 46.9% for Claude Sonnet 4 and 86.1% for Kimi K2.5.
- Kimi K2.5 is cheaper at $0.45 / $2.25 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
- Kimi K2.5 accepts more context: 262K tokens versus 200K.
- Kimi K2.5 has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4 | Kimi K2.5 | |
|---|---|---|
| Provider | Anthropic | Moonshot AI |
| Noometry Index | 40.8 | 48.1 |
| Released | 2025-05-22 | 2026-01-27 |
| Weights | Proprietary | Open |
| Context window | 200K | 262K |
| Max output | 64K | 262K |
| Input $ / M tokens | $3 | $0.45 |
| Output $ / M tokens | $15 | $2.25 |
| Results tracked | 58 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 leads
Claude Sonnet 4: 43.5 (#88), Kimi K2.5: 48.8 (#53)
| Benchmark | Claude Sonnet 4 | Kimi K2.5 |
|---|---|---|
| SWE-bench Verified (bash only) | 64.9% | 70.8% |
| SciCode | 40% | 49% |
| WeirdML | 46.1% | 45.6% |
| LMArena Coding | 1414 | 1474 |
| ALE-Bench | 655.35 | 821.65 |
| SWE-bench Verified | — | 73.8% |
| Aider Polyglot | 61.3% | — |
| LMArena WebDev | — | 1437 |
| SWE-bench Multilingual | — | 67.3% |
| GSO | 4.9% | — |
Agentic & Tool Use Claude Sonnet 4 leads
Claude Sonnet 4: 38.5 (#31), Kimi K2.5: 34.2 (#48)
| Benchmark | Claude Sonnet 4 | Kimi K2.5 |
|---|---|---|
| OSWorld | 43.9% | 63.3% |
| Terminal-Bench | — | 43.2% |
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| METR Time Horizons | 62% | — |
| Vending-Bench 2 | — | 1,198 |
Reasoning Kimi K2.5 leads
Claude Sonnet 4: 22.9 (#187), Kimi K2.5: 31.2 (#80)
| Benchmark | Claude Sonnet 4 | Kimi K2.5 |
|---|---|---|
| ARC-AGI-2 | 5.9% | 11.8% |
| SimpleBench | 45.5% | 46.8% |
| Kagi LLM Benchmark | 73% | 78.5% |
| ARC-AGI-1 | 40% | 65.3% |
| CritPt | 0.3% | 3.1% |
| EnigmaEval | 3.1% | 3.4% |
| LMArena Hard Prompts | 1372 | 1453 |
| Epoch Capabilities Index | 141.69 | 148.03 |
| NYT Connections (extended) | — | 69.9% |
| Chess Puzzles | — | 12% |
| Thematic Generalization | — | 69.4% |
| DTBench | 77.1% | — |
| LMCA | 29% | — |
| ForecastBench | 60.2 | — |
Math Kimi K2.5 leads
Claude Sonnet 4: 43.3 (#80), Kimi K2.5: 51.8 (#53)
| Benchmark | Claude Sonnet 4 | Kimi K2.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 92.2% |
| LMArena Math | 1375 | 1470 |
| FrontierMath (Feb 2025 set) | 4.1% | 27.9% |
| FrontierMath Tier 4 (v1) | 0% | 4.2% |
| MathArena Final-Answer Competitions | — | 62.3% |
| Omni-MATH | 60.2% | — |
| MATH Level 5 | 84.4% | — |
Knowledge Kimi K2.5 leads
Claude Sonnet 4: 41.8 (#108), Kimi K2.5: 53.6 (#56)
| Benchmark | Claude Sonnet 4 | Kimi K2.5 |
|---|---|---|
| GPQA Diamond | 79.2% | 87.6% |
| Humanity's Last Exam | 7.8% | 24.4% |
| Vectara Hallucination Rate | 10.3% | 14.2% |
| LMArena Expert | 1372 | 1466 |
| SimpleQA Verified | — | 34.3% |
| MMLU-Pro | 84.3% | — |
| Confabulations | 13.2% | — |
| GPQA (HELM) | 70.6% | — |
Multimodal Kimi K2.5 leads
Claude Sonnet 4: 26.2 (#121), Kimi K2.5: 41.1 (#39)
| Benchmark | Claude Sonnet 4 | Kimi K2.5 |
|---|---|---|
| LMArena Vision | 1191 | 1269 |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| LMArena Document | — | 1430 |
| MindCube | 44.8% | — |
Multilingual Kimi K2.5 leads
Claude Sonnet 4: 46.7 (#156), Kimi K2.5: 53.9 (#53)
| Benchmark | Claude Sonnet 4 | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 1333 | 1433 |
| LMArena Chinese | 1350 | 1495 |
| LMArena French | 1363 | 1454 |
| LMArena German | 1331 | 1441 |
| LMArena Japanese | 1302 | 1421 |
| LMArena Korean | 1291 | 1410 |
| LMArena Russian | 1355 | 1435 |
| LMArena Spanish | 1357 | 1450 |
Instruction Following Kimi K2.5 leads
Claude Sonnet 4: 71.7 (#145), Kimi K2.5: 75.3 (#64)
| Benchmark | Claude Sonnet 4 | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1376 | 1431 |
| IFEval | 84% | — |
Long Context Kimi K2.5 leads
Claude Sonnet 4: 33.7 (#259), Kimi K2.5: 52.1 (#7)
| Benchmark | Claude Sonnet 4 | Kimi K2.5 |
|---|---|---|
| Fiction.LiveBench | 46.9% | 86.1% |
| LMArena Longer Query | 1398 | 1445 |
| CL-bench | — | 19.3% |
| CL-bench Life | — | 13.2% |
Writing & Preference Kimi K2.5 leads
Claude Sonnet 4: 57.1 (#132), Kimi K2.5: 65.1 (#53)
| Benchmark | Claude Sonnet 4 | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1351 | 1445 |
| LMArena Creative Writing | 1345 | 1423 |
| EQ-Bench Creative Writing | 1483 | 1579 |
| LMArena Multi-Turn | 1376 | 1444 |
| Short-Story Creative Writing | 81.4% | — |
| WildBench | 83.8% | — |
Frequently asked questions
Is Claude Sonnet 4 better than Kimi K2.5?
Kimi K2.5 is the stronger model overall, scoring 48.1 to 40.8 on the Noometry Index.
Which is cheaper, Claude Sonnet 4 or Kimi K2.5?
Kimi K2.5 is cheaper. It lists at $0.45 per million input tokens and $2.25 per million output tokens; Claude Sonnet 4 lists at $3 and $15.
Is Claude Sonnet 4 or Kimi K2.5 better for coding?
Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 43.5 in the Noometry coding category.
Which has the bigger context window?
Kimi K2.5 does, with 262K tokens against 200K.
How many benchmarks do Claude Sonnet 4 and Kimi K2.5 share?
38 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Kimi K2.5 has 51.