GPT-6 Sol scores 62.8 on the Respan Index (#8), ahead of Kimi K2.6 at 34.4 (#55). GPT-6 Sol leads on 18 of the 19 benchmarks both report. Kimi K2.6 is 2.3x 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
| GPQA Diamond |
| 94.3% |
| 90.8% |
| LiveBench Agentic Coding (LiveBench) | 52.9% | 46.9% |
| LiveBench Coding (LiveBench) | 81.8% | 78.6% |
| LiveBench Data Analysis (LiveBench) | 81.2% | 65.1% |
| LiveBench Instruction Following (LiveBench) | 68.6% | 64.4% |
| LiveBench Language (LiveBench) | 85.3% | 75.1% |
| LiveBench Mathematics (LiveBench) | 96.4% | 84.3% |
| LiveBench Reasoning (LiveBench) | 88.7% | 79.4% |
| Mystery Game Puzzles (Epoch AI) | 56% | 18% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 96.1% |
| SAGE (Vals AI) | 44.8% | 50.2% |
| SimpleQA Verified | 60.7% | 34.9% |
| Vending-Bench 2 (Andon Labs) | 14427.85 | 6204.57 |
| LMArena Elo | 1457 | 1455 |
| LMArena WebDev (LMArena) | 1689 | 1509 |
Higher is better. Each score links to where it was published.