Claude Opus 5.5 scores 72.4 on the Respan Index (#1), ahead of Claude Opus 4.8 at 52.2 (#16). Claude Opus 5.5 leads on 21 of the 24 benchmarks both report. Claude Opus 5.5 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) |
| 42.5% |
| 83.3% |
| GPQA Diamond | 93.6% | 90.6% |
| LiveBench Agentic Coding (LiveBench) | 50.5% | 71.7% |
| LiveBench Coding (LiveBench) | 81.8% | 89.3% |
| LiveBench Data Analysis (LiveBench) | 66% | 80.3% |
| LiveBench Instruction Following (LiveBench) | 72% | 67% |
| LiveBench Language (LiveBench) | 79.7% | 86.3% |
| LiveBench Mathematics (LiveBench) | 94.3% | 97.1% |
| LiveBench Reasoning (LiveBench) | 89.2% | 92.2% |
| Mystery Game Puzzles (Epoch AI) | 36% | 71% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 98.3% | 100% |
| SAGE (Vals AI) | 54.8% | 45.8% |
| SimpleQA Verified | 53% | 72.2% |
| Terminal-Bench 4.0 (Vals AI) | 23.2% | 65.2% |
| Vending-Bench 2 (Andon Labs) | 5787.43 | 9235.25 |
| LMArena Agent (LMArena) | 0.0664 | 0.1382 |
| LMArena Elo | 1453 | 1504 |
| LMArena WebDev (LMArena) | 1556 | 1815 |
| SimpleBench (SimpleBench) | 64.8% | 88.4% |
| Humanity's Last Exam (with tools) | 57.9% | 67.7% |
Higher is better. Each score links to where it was published.