Claude Opus 5.5 scores 72.4 on the Respan Index (#1), ahead of DeepSeek V4 Pro at 46.9 (#29). Claude Opus 5.5 leads on 19 of the 21 benchmarks both report. DeepSeek V4 Pro is 4.0x cheaper per token at list price.
* Estimated: no published scores in that category. How the Respan Index works
| LiveBench Agentic Coding (LiveBench) |
| 71.7% |
| 54.9% |
| LiveBench Coding (LiveBench) | 89.3% | 77.2% |
| LiveBench Data Analysis (LiveBench) | 80.3% | 79.2% |
| LiveBench Instruction Following (LiveBench) | 67% | 67.7% |
| LiveBench Language (LiveBench) | 86.3% | 82.1% |
| LiveBench Mathematics (LiveBench) | 97.1% | 95.1% |
| LiveBench Reasoning (LiveBench) | 92.2% | 85.8% |
| Mystery Game Puzzles (Epoch AI) | 71% | 43% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 96.7% |
| SimpleQA Verified | 72.2% | 47% |
| Terminal-Bench 4.0 (Vals AI) | 65.2% | 14.1% |
| Vending-Bench 2 (Andon Labs) | 9235.25 | 3284.52 |
| LMArena Agent (LMArena) | 0.1382 | 0.0119 |
| LMArena Elo | 1504 | 1451 |
| LMArena WebDev (LMArena) | 1815 | 1583 |
| SimpleBench (SimpleBench) | 88.4% | 50.9% |
| Humanity's Last Exam (with tools) | 67.7% | 60% |
Higher is better. Each score links to where it was published.