Model comparison
Claude Opus 4 vs Kimi K2.6
Kimi K2.6 is the stronger model overall, scoring 47.7 to 43.1 on the Noometry Index.
Last verified . 30 shared benchmarks.
Summary
- They share 30 benchmarks with published results for both. Claude Opus 4 scores higher in 2 categories and Kimi K2.6 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.6 leads 57.0 to 42.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 64.4% for Claude Opus 4 and 96.1% for Kimi K2.6.
- Kimi K2.6 is cheaper at $0.95 / $4 per million input/output tokens, against $15 / $75 for Claude Opus 4.
- Kimi K2.6 accepts more context: 262K tokens versus 200K.
- Kimi K2.6 has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4 | Kimi K2.6 | |
|---|---|---|
| Provider | Anthropic | Moonshot AI |
| Noometry Index | 43.1 | 47.7 |
| Released | 2025-05-22 | 2026-04-20 |
| Weights | Proprietary | Open |
| Context window | 200K | 262K |
| Max output | 32K | 262K |
| Input $ / M tokens | $15 | $0.95 |
| Output $ / M tokens | $75 | $4 |
| Results tracked | 56 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.6 leads
Claude Opus 4: 47.2 (#62), Kimi K2.6: 50.7 (#43)
| Benchmark | Claude Opus 4 | Kimi K2.6 |
|---|---|---|
| SWE-bench Verified | 70.7% | 76.7% |
| WeirdML | 43.7% | 55.9% |
| LMArena Coding | 1442 | 1488 |
| SWE-bench Verified (bash only) | 67.6% | — |
| Aider Polyglot | 72% | — |
| LMArena WebDev | — | 1509 |
| SciCode | — | 53.5% |
| GSO | 6.9% | — |
| ALE-Bench | — | 1,093 |
| AlgoTune | 1.33 | — |
Agentic & Tool Use Claude Opus 4 leads
Claude Opus 4: 34.8 (#42), Kimi K2.6: 21.9 (#137)
| Benchmark | Claude Opus 4 | Kimi K2.6 |
|---|---|---|
| OSWorld 2.0 | — | 4.6% |
| Cybench | 38% | — |
| DeepResearch Bench | 46.8% | — |
| ExploitBench | — | 18.4% |
| GBAEval | — | 0.9% |
| GDP.pdf | — | 12% |
| LMArena Search | 1127 | — |
| METR Time Horizons | 63.9% | — |
| Vending-Bench 2 | — | 6,205 |
Reasoning Kimi K2.6 leads
Claude Opus 4: 27.3 (#121), Kimi K2.6: 40.5 (#55)
| Benchmark | Claude Opus 4 | Kimi K2.6 |
|---|---|---|
| CritPt | 0.3% | 8% |
| LMArena Hard Prompts | 1399 | 1470 |
| DTBench | 81.6% | 90.9% |
| LMCA | 37.4% | 37.3% |
| Epoch Capabilities Index | 142.67 | 151.05 |
| ARC-AGI-2 | 8.6% | — |
| SimpleBench | 58.8% | — |
| Kagi LLM Benchmark | 74.3% | — |
| NYT Connections (extended) | — | 87.2% |
| ARC-AGI-1 | 35.7% | — |
| Chess Puzzles | — | 26% |
| EnigmaEval | 5.6% | — |
| EBR-Bench | — | 2.4% |
| Mystery Game Puzzles | — | 18% |
| ForecastBench | 61.1 | — |
Math Kimi K2.6 leads
Claude Opus 4: 42.0 (#86), Kimi K2.6: 57.0 (#41)
| Benchmark | Claude Opus 4 | Kimi K2.6 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 64.4% | 96.1% |
| LMArena Math | 1390 | 1475 |
| FrontierMath (Feb 2025 set) | 4.5% | 39% |
| FrontierMath Tier 4 (v1) | 4.2% | 14.6% |
| FrontierMath (Tiers 1-3) | — | 57.2% |
| FrontierMath Tier 4 | — | 25.6% |
| MathArena Final-Answer Competitions | — | 72.9% |
| ProofBench | — | 16% |
| Omni-MATH | 61.6% | — |
| MATH Level 5 | 85% | — |
Knowledge Kimi K2.6 leads
Claude Opus 4: 44.0 (#88), Kimi K2.6: 54.0 (#54)
| Benchmark | Claude Opus 4 | Kimi K2.6 |
|---|---|---|
| GPQA Diamond | 76.3% | 90.8% |
| Vectara Hallucination Rate | 12% | 10.8% |
| LMArena Expert | 1386 | 1491 |
| Humanity's Last Exam | 10.7% | — |
| SimpleQA Verified | — | 34.9% |
| MMLU-Pro | 87.5% | — |
| Confabulations | 15.9% | — |
| GPQA (HELM) | 70.8% | — |
Multimodal Too close to call
Claude Opus 4: 31.5 (#106), Kimi K2.6: 31.6 (#103)
| Benchmark | Claude Opus 4 | Kimi K2.6 |
|---|---|---|
| LMArena Vision | 1192 | 1283 |
| GeoBench | 49% | — |
| VPCT | 38% | — |
| Blueprint-Bench 2 | — | 3.9% |
| Furniture Assembly | — | 21.7% |
| LMArena Document | — | 1451 |
Multilingual Kimi K2.6 leads
Claude Opus 4: 48.8 (#138), Kimi K2.6: 54.9 (#37)
| Benchmark | Claude Opus 4 | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | 1362 | 1446 |
| LMArena Chinese | 1386 | 1521 |
| LMArena French | 1372 | 1471 |
| LMArena German | 1391 | 1450 |
| LMArena Japanese | 1331 | 1443 |
| LMArena Korean | 1321 | 1427 |
| LMArena Russian | 1392 | 1446 |
| LMArena Spanish | 1389 | 1464 |
Instruction Following Too close to call
Claude Opus 4: 77.1 (#28), Kimi K2.6: 76.3 (#43)
| Benchmark | Claude Opus 4 | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | 1406 | 1451 |
| IFEval | 91.8% | — |
Long Context Kimi K2.6 leads
Claude Opus 4: 39.6 (#172), Kimi K2.6: 44.9 (#52)
| Benchmark | Claude Opus 4 | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | 1422 | 1468 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference Kimi K2.6 leads
Claude Opus 4: 61.2 (#89), Kimi K2.6: 68.5 (#26)
| Benchmark | Claude Opus 4 | Kimi K2.6 |
|---|---|---|
| LMArena Text | 1377 | 1455 |
| LMArena Creative Writing | 1387 | 1434 |
| EQ-Bench Creative Writing | 1580 | 1725 |
| LMArena Multi-Turn | 1396 | 1453 |
| Short-Story Creative Writing | 83.6% | — |
| WildBench | 85.2% | — |
| EQ-Bench 4 | — | 1202 |
Frequently asked questions
Is Claude Opus 4 better than Kimi K2.6?
Kimi K2.6 is the stronger model overall, scoring 47.7 to 43.1 on the Noometry Index.
Which is cheaper, Claude Opus 4 or Kimi K2.6?
Kimi K2.6 is cheaper. It lists at $0.95 per million input tokens and $4 per million output tokens; Claude Opus 4 lists at $15 and $75.
Is Claude Opus 4 or Kimi K2.6 better for coding?
Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 47.2 in the Noometry coding category.
Which has the bigger context window?
Kimi K2.6 does, with 262K tokens against 200K.
How many benchmarks do Claude Opus 4 and Kimi K2.6 share?
30 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and Kimi K2.6 has 51.