Claude Sonnet 5.5 scores 68.5 on the Respan Index (#6), ahead of Qwen3.8-Max at 50.3 (#22). Claude Sonnet 5.5 leads on 18 of the 22 benchmarks both report. Qwen3.8-Max is 1.3x cheaper per token at list price.
* Estimated: no published scores in that category. How the Respan Index works
| Furniture Assembly (Epoch AI) |
| 75% |
| 20% |
| GPQA Diamond | 95.6% | 92.6% |
| LiveBench Agentic Coding (LiveBench) | 56.3% | 64.6% |
| LiveBench Coding (LiveBench) | 91.4% | 72.9% |
| LiveBench Data Analysis (LiveBench) | 78.6% | 78.4% |
| LiveBench Instruction Following (LiveBench) | 70.5% | 74.1% |
| LiveBench Language (LiveBench) | 83.4% | 79.7% |
| LiveBench Mathematics (LiveBench) | 96.7% | 91.3% |
| LiveBench Reasoning (LiveBench) | 91.6% | 88.2% |
| Mystery Game Puzzles (Epoch AI) | 65% | 38% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 99.4% |
| SAGE (Vals AI) | 51.8% | 51.3% |
| SimpleQA Verified | 46.5% | 45.8% |
| Terminal-Bench 4.0 (Vals AI) | 64.1% | 34.3% |
| LMArena Agent (LMArena) | 0.1252 | 0.0251 |
| LMArena Elo | 1471 | 1481 |
| LMArena Vision (LMArena) | 1268 | 1301 |
| LMArena WebDev (LMArena) | 1786 | 1671 |
Higher is better. Each score links to where it was published.