GPT-5.6 Sol scores 60.6 on the Respan Index (#10), ahead of Muse Spark 1.3 at 54.1 (#13). GPT-5.6 Sol leads on 12 of the 19 benchmarks both report. Muse Spark 1.3 is 4.0x 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 Agentic Coding (LiveBench) |
| 56.2% |
| 64.1% |
| LiveBench Coding (LiveBench) | 83.9% | 81.1% |
| LiveBench Data Analysis (LiveBench) | 79.8% | 79.6% |
| LiveBench Instruction Following (LiveBench) | 71.8% | 78% |
| LiveBench Language (LiveBench) | 87.7% | 82.8% |
| LiveBench Mathematics (LiveBench) | 96.2% | 95.9% |
| LiveBench Reasoning (LiveBench) | 91.7% | 89.7% |
| Mystery Game Puzzles (Epoch AI) | 58% | 25% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 99.2% |
| Terminal-Bench 4.0 (Vals AI) | 37.9% | 24.7% |
| LMArena Agent (LMArena) | 0.0645 | 0.04 |
| LMArena Elo | 1484 | 1494 |
| LMArena Vision (LMArena) | 1285 | 1290 |
| DeepSWE v1.1 | 72.7% | 75.4% |
| SimpleBench (SimpleBench) | 71.7% | 81.8% |
Higher is better. Each score links to where it was published.