GPT-6 Sol scores 62.8 on the Respan Index (#8), ahead of Claude Opus 4.8 at 52.2 (#16). GPT-6 Sol leads on 19 of the 23 benchmarks both report. GPT-6 Sol is 2.5x 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
| Furniture Assembly (Epoch AI) |
| 42.5% |
| 58.3% |
| GPQA Diamond | 93.6% | 94.3% |
| LiveBench Agentic Coding (LiveBench) | 50.5% | 52.9% |
| LiveBench Coding (LiveBench) | 81.8% | 81.8% |
| LiveBench Data Analysis (LiveBench) | 66% | 81.2% |
| LiveBench Instruction Following (LiveBench) | 72% | 68.6% |
| LiveBench Language (LiveBench) | 79.7% | 85.3% |
| LiveBench Mathematics (LiveBench) | 94.3% | 96.4% |
| LiveBench Reasoning (LiveBench) | 89.2% | 88.7% |
| Mystery Game Puzzles (Epoch AI) | 36% | 56% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 98.3% | 100% |
| SAGE (Vals AI) | 54.8% | 44.8% |
| SimpleQA Verified | 53% | 60.7% |
| Terminal-Bench 4.0 (Vals AI) | 23.2% | 44.4% |
| Vending-Bench 2 (Andon Labs) | 5787.43 | 14427.85 |
| LMArena Agent (LMArena) | 0.0664 | 0.0971 |
| LMArena Elo | 1453 | 1457 |
| LMArena WebDev (LMArena) | 1556 | 1689 |
| SimpleBench (SimpleBench) | 64.8% | 73.1% |
Higher is better. Each score links to where it was published.