GPT-6 Sol scores 62.8 on the Respan Index (#8), ahead of Grok 4.6 at 51.0 (#19). GPT-6 Sol leads on 19 of the 24 benchmarks both report. Grok 4.6 is 1.3x 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) |
| 58.3% |
| 40% |
| GPQA Diamond | 94.3% | 94% |
| LiveBench Agentic Coding (LiveBench) | 52.9% | 57% |
| LiveBench Coding (LiveBench) | 81.8% | 76.8% |
| LiveBench Data Analysis (LiveBench) | 81.2% | 73.9% |
| LiveBench Instruction Following (LiveBench) | 68.6% | 71.9% |
| LiveBench Language (LiveBench) | 85.3% | 83.7% |
| LiveBench Mathematics (LiveBench) | 96.4% | 92.6% |
| LiveBench Reasoning (LiveBench) | 88.7% | 90.5% |
| Mystery Game Puzzles (Epoch AI) | 56% | 34% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 99.2% |
| SAGE (Vals AI) | 44.8% | 28.9% |
| SimpleQA Verified | 60.7% | 49.3% |
| Terminal-Bench 4.0 (Vals AI) | 44.4% | 17.2% |
| Vending-Bench 2 (Andon Labs) | 14427.85 | 9047.03 |
| LMArena Agent (LMArena) | 0.0971 | 0.0128 |
| LMArena Elo | 1457 | 1454 |
| LMArena WebDev (LMArena) | 1689 | 1620 |
| SimpleBench (SimpleBench) | 73.1% | 75.9% |
| DeepSWE v1.1 | 68.8% | 65.9% |
Higher is better. Each score links to where it was published.