Claude Opus 4.8 scores 52.2 on the Respan Index (#16), ahead of DeepSeek V4.1 Flash at 50.9 (#20). Claude Opus 4.8 leads on 9 of the 16 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
| LiveBench Data Analysis (LiveBench) |
| 66% |
| 79.3% |
| LiveBench Instruction Following (LiveBench) | 72% | 70% |
| LiveBench Language (LiveBench) | 79.7% | 81.2% |
| LiveBench Mathematics (LiveBench) | 94.3% | 93.3% |
| LiveBench Reasoning (LiveBench) | 89.2% | 86.7% |
| SAGE (Vals AI) | 54.8% | 47.9% |
| Terminal-Bench 4.0 (Vals AI) | 23.2% | 19.7% |
| LMArena Agent (LMArena) | 0.0664 | 0.0402 |
| LMArena Elo | 1453 | 1474 |
| LMArena WebDev (LMArena) | 1556 | 1620 |
| SimpleBench (SimpleBench) | 64.8% | 66.7% |
| Terminal-Bench 2.1 | 74.6% | 90.6% |
Higher is better. Each score links to where it was published.