Claude Sonnet 5.5 scores 68.5 on the Respan Index (#6), ahead of Kimi K2.7 Code at 34.1 (#58). Claude Sonnet 5.5 leads on 15 of the 15 benchmarks both report. Kimi K2.7 Code is 2.3x cheaper per token at list price. Claude Sonnet 5.5 has the larger context window (1M tokens).
* Estimated: no published scores in that category. How the Respan Index works
| LiveBench Agentic Coding (LiveBench) |
| 56.3% |
| 45.7% |
| LiveBench Coding (LiveBench) | 91.4% | 74% |
| LiveBench Data Analysis (LiveBench) | 78.6% | 62.7% |
| LiveBench Instruction Following (LiveBench) | 70.5% | 56.3% |
| LiveBench Language (LiveBench) | 83.4% | 77.9% |
| LiveBench Mathematics (LiveBench) | 96.7% | 79.6% |
| LiveBench Reasoning (LiveBench) | 91.6% | 82.8% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 95.6% |
| SimpleQA Verified | 46.5% | 36.5% |
| LMArena WebDev (LMArena) | 1786 | 1473 |
| SimpleBench (SimpleBench) | 75.9% | 57.9% |
Higher is better. Each score links to where it was published.