Claude Sonnet 5.5 scores 68.5 on the Respan Index (#6), ahead of Kimi K2.6 at 34.4 (#55). Claude Sonnet 5.5 leads on 18 of the 18 benchmarks both report. Kimi K2.6 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% |
| 46.9% |
| LiveBench Coding (LiveBench) | 91.4% | 78.6% |
| LiveBench Data Analysis (LiveBench) | 78.6% | 65.1% |
| LiveBench Instruction Following (LiveBench) | 70.5% | 64.4% |
| LiveBench Language (LiveBench) | 83.4% | 75.1% |
| LiveBench Mathematics (LiveBench) | 96.7% | 84.3% |
| LiveBench Reasoning (LiveBench) | 91.6% | 79.4% |
| Mystery Game Puzzles (Epoch AI) | 65% | 18% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 96.1% |
| SAGE (Vals AI) | 51.8% | 50.2% |
| SimpleQA Verified | 46.5% | 34.9% |
| LMArena Elo | 1471 | 1455 |
| LMArena Vision (LMArena) | 1268 | 1265 |
| LMArena WebDev (LMArena) | 1786 | 1509 |
Higher is better. Each score links to where it was published.