Claude Opus 5.5 scores 72.4 on the Respan Index (#1), ahead of GPT-5.6 Sol at 60.6 (#10). Claude Opus 5.5 leads on 18 of the 24 benchmarks both report. Both cost about the same per token at list price. GPT-5.6 Sol has the larger context window (1.1M tokens).
* Estimated: no published scores in that category. How the Respan Index works
| FrontierSWE V2 (Proximal Labs) |
| 62.3% |
| 32.2% |
| Furniture Assembly (Epoch AI) | 83.3% | 56.7% |
| GPQA Diamond | 90.6% | 94.6% |
| LiveBench Agentic Coding (LiveBench) | 71.7% | 56.2% |
| LiveBench Coding (LiveBench) | 89.3% | 83.9% |
| LiveBench Data Analysis (LiveBench) | 80.3% | 79.8% |
| LiveBench Instruction Following (LiveBench) | 67% | 71.8% |
| LiveBench Language (LiveBench) | 86.3% | 87.7% |
| LiveBench Mathematics (LiveBench) | 97.1% | 96.2% |
| LiveBench Reasoning (LiveBench) | 92.2% | 91.7% |
| MirrorCode (Epoch AI) | 77.4% | 20% |
| Mystery Game Puzzles (Epoch AI) | 71% | 58% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 100% |
| SAGE (Vals AI) | 45.8% | 52.6% |
| SimpleQA Verified | 72.2% | 69.7% |
| Terminal-Bench 4.0 (Vals AI) | 65.2% | 37.9% |
| Vending-Bench 2 (Andon Labs) | 9235.25 | 9619.37 |
| LMArena Agent (LMArena) | 0.1382 | 0.0645 |
| LMArena Elo | 1504 | 1484 |
| SimpleBench (SimpleBench) | 88.4% | 71.7% |
Higher is better. Each score links to where it was published.