GPT-6.1 Sol scores 69.4 on the Respan Index (#4), ahead of Muse Spark 1.3 at 54.1 (#13). GPT-6.1 Sol leads on 15 of the 19 benchmarks both report. Muse Spark 1.3 is 2.0x cheaper per token at list price. GPT-6.1 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) |
| 56.8% |
| 64.1% |
| LiveBench Coding (LiveBench) | 80.7% | 81.1% |
| LiveBench Data Analysis (LiveBench) | 82.7% | 79.6% |
| LiveBench Instruction Following (LiveBench) | 74.2% | 78% |
| LiveBench Language (LiveBench) | 90.1% | 82.8% |
| LiveBench Mathematics (LiveBench) | 96.8% | 95.9% |
| LiveBench Reasoning (LiveBench) | 92.6% | 89.7% |
| Mystery Game Puzzles (Epoch AI) | 80% | 25% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 99.2% |
| Terminal-Bench 4.0 (Vals AI) | 55.1% | 24.7% |
| LMArena Agent (LMArena) | 0.1123 | 0.04 |
| LMArena Elo | 1483 | 1494 |
| LMArena Vision (LMArena) | 1291 | 1290 |
| LMArena WebDev (LMArena) | 1758 | 1657 |
| SimpleBench (SimpleBench) | 82.9% | 81.8% |
Higher is better. Each score links to where it was published.