Claude Opus 5 scores 63.9 on the Respan Index (#7), ahead of DeepSeek V4.1 Flash at 50.9 (#20). Claude Opus 5 leads on 12 of the 15 benchmarks both report. DeepSeek V4.1 Flash is 19x cheaper per token at list price.
* Estimated: no published scores in that category. How the Respan Index works
| 74.6% |
| 79.3% |
| LiveBench Instruction Following (LiveBench) | 63.8% | 70% |
| LiveBench Language (LiveBench) | 88.7% | 81.2% |
| LiveBench Mathematics (LiveBench) | 95.7% | 93.3% |
| LiveBench Reasoning (LiveBench) | 91.2% | 86.7% |
| SAGE (Vals AI) | 49.4% | 47.9% |
| Terminal-Bench 4.0 (Vals AI) | 53.5% | 19.7% |
| LMArena Agent (LMArena) | 0.0867 | 0.0402 |
| LMArena Elo | 1490 | 1474 |
| LMArena WebDev (LMArena) | 1695 | 1620 |
| SimpleBench (SimpleBench) | 80.6% | 66.7% |
Higher is better. Each score links to where it was published.