GPT-5.5 scores 52.5 on the Respan Index (#15), ahead of DeepSeek V4.1 Flash at 50.9 (#20). GPT-5.5 leads on 10 of the 13 benchmarks both report. DeepSeek V4.1 Flash is 21x cheaper per token at list price.
* Estimated: no published scores in that category. How the Respan Index works
| LiveBench Instruction Following (LiveBench) |
| 70% |
| 70.7% |
| LiveBench Language (LiveBench) | 81.2% | 87.4% |
| LiveBench Mathematics (LiveBench) | 93.3% | 95.9% |
| LiveBench Reasoning (LiveBench) | 86.7% | 89.7% |
| SAGE (Vals AI) | 47.9% | 51.5% |
| LMArena Agent (LMArena) | 0.0402 | 0.0415 |
| LMArena Elo | 1474 | 1466 |
| SimpleBench (SimpleBench) | 66.7% | 69% |
| GPQA Diamond | 90.9% | 90.7% |
Higher is better. Each score links to where it was published.