Claude Opus 5.5 scores 72.4 on the Respan Index (#1), ahead of Grok 4.6 at 51.0 (#19). Claude Opus 5.5 leads on 22 of the 24 benchmarks both report. Grok 4.6 is 2.7x cheaper per token at list price. Claude Opus 5.5 has the larger context window (1M tokens).
* Estimated: no published scores in that category. How the Respan Index works
| FrontierSWE V2 (Proximal Labs) |
| 62.3% |
| 25.3% |
| Furniture Assembly (Epoch AI) | 83.3% | 40% |
| GPQA Diamond | 90.6% | 94% |
| LiveBench Agentic Coding (LiveBench) | 71.7% | 57% |
| LiveBench Coding (LiveBench) | 89.3% | 76.8% |
| LiveBench Data Analysis (LiveBench) | 80.3% | 73.9% |
| LiveBench Instruction Following (LiveBench) | 67% | 71.9% |
| LiveBench Language (LiveBench) | 86.3% | 83.7% |
| LiveBench Mathematics (LiveBench) | 97.1% | 92.6% |
| LiveBench Reasoning (LiveBench) | 92.2% | 90.5% |
| Mystery Game Puzzles (Epoch AI) | 71% | 34% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 99.2% |
| SAGE (Vals AI) | 45.8% | 28.9% |
| SimpleQA Verified | 72.2% | 49.3% |
| Terminal-Bench 4.0 (Vals AI) | 65.2% | 17.2% |
| Vending-Bench 2 (Andon Labs) | 9235.25 | 9047.03 |
| LMArena Agent (LMArena) | 0.1382 | 0.0128 |
| LMArena Elo | 1504 | 1454 |
| LMArena WebDev (LMArena) | 1815 | 1620 |
| SimpleBench (SimpleBench) | 88.4% | 75.9% |
Higher is better. Each score links to where it was published.