Up to four models
Claude Opus 4.5 vs Kimi K2.7 Code
On the index (GPT-4 = 100), Claude Opus 4.5 scores 152 and Kimi K2.7 Code 151. 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 4.5
152136–168
WeightsClosed
ReleasedNov 2025
Price in / out$5.0 / $25
Context200K
Core tests taken5 of 9
Kimi K2.7 Code
151135–167
WeightsOpen
ReleasedJun 2026
Price in / out$0.70 / $3.75
Context262K
Core tests taken3 of 9
Claude Opus 4.5 and Kimi K2.7 Code are too close to call (1 point apart, within the uncertainty), ahead on 0 of 2 shared core tests, at 6.8× the price.
Test by testthird-party results
Claude Opus 4.5Kimi K2.7 Code
Every result as a table
| Test | Claude Opus 4.5 | Kimi K2.7 Code |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 86.1% | 87.9% |
| LiveBench Data Analysis | 74.4% | 62.7% |
| LiveBench IF | 62.5% | 56.3% |
| LiveBench Language | 81.3% | 77.9% |
| LiveBench Reasoning | 80.1% | 82.8% |
| SimpleBench | 62.0% | 57.9% |
| SimpleQA Verified | 45.7% | 36.5% |
| Maths | ||
| FrontierMath (tiers 1-3) | 34.4% | 54.0% |
| AIME-style maths (OTIS mock) | 86.1% | 95.6% |
| LiveBench Mathematics | 90.4% | 79.6% |
| Chess puzzles | 14.0% | 14.0% |
| FrontierMath (tier 4) | 4.9% | 12.2% |
| Coding | ||
| LiveBench Agentic Coding | 39.7% | 45.7% |
| LiveBench Coding | 79.7% | 74.0% |
| LiveCodeBench | 83.7% | 82.0% |
| SWE-bench | 76.4% | 78.2% |
| Vibe Code Bench v1.1 | 20.6% | 47.2% |
| WeirdML | 63.7% | 54.1% |
Task length · METR45 sec
Tests at least two of these models have taken. Bold rows are the core tests.