GPT-5.6 Sol scores 60.6 on the Respan Index (#10), ahead of DeepSeek V4.1 Flash at 50.9 (#20). GPT-5.6 Sol leads on 13 of the 15 benchmarks both report. DeepSeek V4.1 Flash is 15x cheaper per token at list price. GPT-5.6 Sol has the larger context window (1.1M tokens).
* Estimated: no published scores in that category. How the Respan Index works
| LiveBench Instruction Following (LiveBench) |
| 70% |
| 71.8% |
| LiveBench Language (LiveBench) | 81.2% | 87.7% |
| LiveBench Mathematics (LiveBench) | 93.3% | 96.2% |
| LiveBench Reasoning (LiveBench) | 86.7% | 91.7% |
| SAGE (Vals AI) | 47.9% | 52.6% |
| Terminal-Bench 4.0 (Vals AI) | 19.7% | 37.9% |
| LMArena Agent (LMArena) | 0.0402 | 0.0645 |
| LMArena Elo | 1474 | 1484 |
| SimpleBench (SimpleBench) | 66.7% | 71.7% |
| DeepSWE v1.1 | 74.2% | 72.7% |
| GPQA Diamond | 90.9% | 94.6% |
Higher is better. Each score links to where it was published.