Up to four models
Claude Opus 4.1 vs Kimi K2 Thinking
On the index (GPT-4 = 100), Claude Opus 4.1 scores 140 and Kimi K2 Thinking 139. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
Claude Opus 4.1
140124–156
WeightsClosed
ReleasedAug 2025
Price in / out$15 / $75
Context200K
Core tests taken5 of 9
Kimi K2 Thinking
139123–156
WeightsOpen
ReleasedNov 2025
Price in / out$0.60 / $2.5
Context262K
Core tests taken2 of 9
Claude Opus 4.1 and Kimi K2 Thinking are too close to call (1 point apart, within the uncertainty), ahead on 1 of 2 shared core tests, at 28× the price.
Test by testthird-party results
Claude Opus 4.1Kimi K2 Thinking
Every result as a table
| Test | Claude Opus 4.1 | Kimi K2 Thinking |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 77.3% | 84.2% |
| SimpleBench | 60.0% | 39.6% |
| Maths | ||
| AIME-style maths (OTIS mock) | 68.9% | 83.1% |
| FrontierMath (2025 set) | 7.2% | 21.4% |
| FrontierMath tier 4 (2025 set) | 4.2% | 0.0% |
| Coding | ||
| Terminal-Bench 2.0 (Terminus 2 runs) | 38.0% | 35.7% |
| WeirdML | 45.9% | 42.8% |
Task length · METR40 sec36 sec
Tests at least two of these models have taken. Bold rows are the core tests.