Claude Opus 5.5 scores 72.4 on the Respan Index (#1), ahead of Qwen3.7-Max at 40.5 (#45). Claude Opus 5.5 leads on 15 of the 17 benchmarks both report. Qwen3.7-Max is 2.1x cheaper per token at list price.
* Estimated: no published scores in that category. How the Respan Index works
| 71.7% |
| 43.6% |
| LiveBench Coding (LiveBench) | 89.3% | 74.2% |
| LiveBench Data Analysis (LiveBench) | 80.3% | 71.8% |
| LiveBench Instruction Following (LiveBench) | 67% | 74% |
| LiveBench Language (LiveBench) | 86.3% | 79.7% |
| LiveBench Mathematics (LiveBench) | 97.1% | 85.2% |
| LiveBench Reasoning (LiveBench) | 92.2% | 83.3% |
| Mystery Game Puzzles (Epoch AI) | 71% | 32% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 95.6% |
| SimpleQA Verified | 72.2% | 55.8% |
| LMArena Agent (LMArena) | 0.1382 | -0.0513 |
| LMArena WebDev (LMArena) | 1815 | 1515 |
| SimpleBench (SimpleBench) | 88.4% | 70.4% |
Higher is better. Each score links to where it was published.