Claude Opus 5.5 scores 72.4 on the Respan Index (#1), ahead of Qwen3.8-Max at 50.3 (#22). Claude Opus 5.5 leads on 18 of the 21 benchmarks both report. Qwen3.8-Max is 2.7x cheaper per token at list price.
* Estimated: no published scores in that category. How the Respan Index works
| Furniture Assembly (Epoch AI) |
| 83.3% |
| 20% |
| GPQA Diamond | 90.6% | 92.6% |
| LiveBench Agentic Coding (LiveBench) | 71.7% | 64.6% |
| LiveBench Coding (LiveBench) | 89.3% | 72.9% |
| LiveBench Data Analysis (LiveBench) | 80.3% | 78.4% |
| LiveBench Instruction Following (LiveBench) | 67% | 74.1% |
| LiveBench Language (LiveBench) | 86.3% | 79.7% |
| LiveBench Mathematics (LiveBench) | 97.1% | 91.3% |
| LiveBench Reasoning (LiveBench) | 92.2% | 88.2% |
| Mystery Game Puzzles (Epoch AI) | 71% | 38% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 99.4% |
| SAGE (Vals AI) | 45.8% | 51.3% |
| SimpleQA Verified | 72.2% | 45.8% |
| Terminal-Bench 4.0 (Vals AI) | 65.2% | 34.3% |
| LMArena Agent (LMArena) | 0.1382 | 0.0251 |
| LMArena Elo | 1504 | 1481 |
| LMArena WebDev (LMArena) | 1815 | 1671 |
Higher is better. Each score links to where it was published.