GPT-6 Sol scores 62.8 on the Respan Index (#8), ahead of Muse Spark 1.3 at 54.1 (#13). GPT-6 Sol leads on 11 of the 18 benchmarks both report. Muse Spark 1.3 is 2.0x cheaper per token at list price. GPT-6 Sol has the larger context window (1.1M tokens).
* Estimated: no published scores in that category. How the Respan Index works
| LiveBench Coding (LiveBench) | 81.8% | 81.1% |
| LiveBench Data Analysis (LiveBench) | 81.2% | 79.6% |
| LiveBench Instruction Following (LiveBench) | 68.6% | 78% |
| LiveBench Language (LiveBench) | 85.3% | 82.8% |
| LiveBench Mathematics (LiveBench) | 96.4% | 95.9% |
| LiveBench Reasoning (LiveBench) | 88.7% | 89.7% |
| Mystery Game Puzzles (Epoch AI) | 56% | 25% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 99.2% |
| Terminal-Bench 4.0 (Vals AI) | 44.4% | 24.7% |
| LMArena Agent (LMArena) | 0.0971 | 0.04 |
| LMArena Elo | 1457 | 1494 |
| LMArena WebDev (LMArena) | 1689 | 1657 |
| SimpleBench (SimpleBench) | 73.1% | 81.8% |
| DeepSWE v1.1 | 68.8% | 75.4% |
Higher is better. Each score links to where it was published.