Model comparison
Claude Opus 4.1 vs Kimi K2.6
Kimi K2.6 is the stronger model overall, scoring 47.7 to 41.0 on the Noometry Index.
Last verified . 34 shared benchmarks.
Summary
- They share 34 benchmarks with published results for both. Claude Opus 4.1 scores higher in 1 category and Kimi K2.6 in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.6 leads 57.0 to 22.3.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 12.6% for Claude Opus 4.1 and 57.2% for Kimi K2.6.
- Kimi K2.6 is cheaper at $0.95 / $4 per million input/output tokens, against $15 / $75 for Claude Opus 4.1.
- 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 4.1 | Kimi K2.6 | |
|---|---|---|
| Provider | Anthropic | Moonshot AI |
| Noometry Index | 41.0 | 47.7 |
| Released | 2025-08-05 | 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 | 48 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.6 leads
Claude Opus 4.1: 44.4 (#73), Kimi K2.6: 50.7 (#43)
| Benchmark | Claude Opus 4.1 | Kimi K2.6 |
|---|---|---|
| SWE-bench Verified | 73.3% | 76.7% |
| LMArena WebDev | 1390 | 1509 |
| WeirdML | 45.9% | 55.9% |
| LMArena Coding | 1479 | 1488 |
| ALE-Bench | 674.77 | 1,093 |
| SciCode | — | 53.5% |
| AlgoTune | 1.34 | — |
Agentic & Tool Use Claude Opus 4.1 leads
Claude Opus 4.1: 35.0 (#41), Kimi K2.6: 21.9 (#137)
| Benchmark | Claude Opus 4.1 | Kimi K2.6 |
|---|---|---|
| Terminal-Bench | 38% | — |
| OSWorld 2.0 | — | 4.6% |
| GDPval | 43.6% | — |
| Cybench | 42% | — |
| DeepResearch Bench | 48.3% | — |
| ExploitBench | — | 18.4% |
| GBAEval | — | 0.9% |
| GDP.pdf | — | 12% |
| LMArena Search | 1148 | — |
| METR Time Horizons | 66.8% | — |
| Vending-Bench 2 | — | 6,205 |
Reasoning Kimi K2.6 leads
Claude Opus 4.1: 32.2 (#76), Kimi K2.6: 40.5 (#55)
| Benchmark | Claude Opus 4.1 | Kimi K2.6 |
|---|---|---|
| Chess Puzzles | 7% | 26% |
| EBR-Bench | 7.9% | 2.4% |
| LMArena Hard Prompts | 1443 | 1470 |
| Mystery Game Puzzles | 21% | 18% |
| DTBench | 80% | 90.9% |
| LMCA | 37.1% | 37.3% |
| Epoch Capabilities Index | 144.12 | 151.05 |
| SimpleBench | 60% | — |
| NYT Connections (extended) | — | 87.2% |
| CritPt | — | 8% |
| EnigmaEval | 7.2% | — |
| ForecastBench | 62 | — |
Math Kimi K2.6 leads
Claude Opus 4.1: 22.3 (#277), Kimi K2.6: 57.0 (#41)
| Benchmark | Claude Opus 4.1 | Kimi K2.6 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 12.6% | 57.2% |
| FrontierMath Tier 4 | 2.4% | 25.6% |
| OTIS Mock AIME 2024-2025 | 68.9% | 96.1% |
| LMArena Math | 1431 | 1475 |
| FrontierMath (Feb 2025 set) | 7.2% | 39% |
| FrontierMath Tier 4 (v1) | 4.2% | 14.6% |
| MathArena Final-Answer Competitions | — | 72.9% |
| ProofBench | — | 16% |
Knowledge Kimi K2.6 leads
Claude Opus 4.1: 42.0 (#101), Kimi K2.6: 54.0 (#54)
| Benchmark | Claude Opus 4.1 | Kimi K2.6 |
|---|---|---|
| GPQA Diamond | 77.3% | 90.8% |
| Vectara Hallucination Rate | 11.8% | 10.8% |
| LMArena Expert | 1439 | 1491 |
| Humanity's Last Exam | 11.5% | — |
| SimpleQA Verified | — | 34.9% |
| Confabulations | 17.1% | — |
Multimodal Kimi K2.6 leads
Claude Opus 4.1: 26.8 (#119), Kimi K2.6: 31.6 (#103)
| Benchmark | Claude Opus 4.1 | Kimi K2.6 |
|---|---|---|
| LMArena Vision | — | 1283 |
| VPCT | 35% | — |
| Blueprint-Bench 2 | — | 3.9% |
| Furniture Assembly | — | 21.7% |
| LMArena Document | — | 1451 |
Multilingual Kimi K2.6 leads
Claude Opus 4.1: 52.0 (#95), Kimi K2.6: 54.9 (#37)
| Benchmark | Claude Opus 4.1 | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | 1405 | 1446 |
| LMArena Chinese | 1427 | 1521 |
| LMArena French | 1431 | 1471 |
| LMArena German | 1413 | 1450 |
| LMArena Japanese | 1378 | 1443 |
| LMArena Korean | 1380 | 1427 |
| LMArena Russian | 1422 | 1446 |
| LMArena Spanish | 1448 | 1464 |
Instruction Following Too close to call
Claude Opus 4.1: 75.6 (#58), Kimi K2.6: 76.3 (#43)
| Benchmark | Claude Opus 4.1 | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | 1435 | 1451 |
Long Context Too close to call
Claude Opus 4.1: 44.5 (#63), Kimi K2.6: 44.9 (#52)
| Benchmark | Claude Opus 4.1 | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | 1455 | 1468 |
Writing & Preference Kimi K2.6 leads
Claude Opus 4.1: 62.4 (#74), Kimi K2.6: 68.5 (#26)
| Benchmark | Claude Opus 4.1 | Kimi K2.6 |
|---|---|---|
| LMArena Text | 1419 | 1455 |
| LMArena Creative Writing | 1412 | 1434 |
| LMArena Multi-Turn | 1444 | 1453 |
| Short-Story Creative Writing | 84.7% | — |
| EQ-Bench Creative Writing | — | 1725 |
| EQ-Bench 4 | — | 1202 |
Frequently asked questions
Is Claude Opus 4.1 better than Kimi K2.6?
Kimi K2.6 is the stronger model overall, scoring 47.7 to 41.0 on the Noometry Index.
Which is cheaper, Claude Opus 4.1 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 4.1 lists at $15 and $75.
Is Claude Opus 4.1 or Kimi K2.6 better for coding?
Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 44.4 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 4.1 and Kimi K2.6 share?
34 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and Kimi K2.6 has 51.