Claude Sonnet 5.5 scores 68.5 on the Respan Index (#6), ahead of DeepSeek V4 Flash at 43.3 (#37). Claude Sonnet 5.5 leads on 16 of the 17 benchmarks both report.
* Estimated: no published scores in that category. How the Respan Index works
| LiveBench Coding (LiveBench) |
| 91.4% |
| 75% |
| LiveBench Data Analysis (LiveBench) | 78.6% | 79.3% |
| LiveBench Instruction Following (LiveBench) | 70.5% | 65.5% |
| LiveBench Language (LiveBench) | 83.4% | 79.2% |
| LiveBench Mathematics (LiveBench) | 96.7% | 86.8% |
| LiveBench Reasoning (LiveBench) | 91.6% | 86.6% |
| Mystery Game Puzzles (Epoch AI) | 65% | 34% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 94.4% |
| SimpleQA Verified | 46.5% | 33.6% |
| Terminal-Bench 4.0 (Vals AI) | 64.1% | 18.7% |
| LMArena Elo | 1471 | 1436 |
| LMArena WebDev (LMArena) | 1786 | 1581 |
| SimpleBench (SimpleBench) | 75.9% | 61.1% |
Higher is better. Each score links to where it was published.