GPT-6 Astra scores 70.5 on the Respan Index (#2), ahead of DeepSeek V4 Flash at 43.3 (#37). GPT-6 Astra leads on 20 of the 20 benchmarks both report. GPT-6 Astra has the larger context window (1.1M tokens).
* Estimated: no published scores in that category. How the Respan Index works
| GPQA Diamond |
| 91% |
| 96% |
| LiveBench Agentic Coding (LiveBench) | 46.8% | 57.3% |
| LiveBench Coding (LiveBench) | 75% | 80.4% |
| LiveBench Data Analysis (LiveBench) | 79.3% | 83% |
| LiveBench Instruction Following (LiveBench) | 65.5% | 75.6% |
| LiveBench Language (LiveBench) | 79.2% | 89.4% |
| LiveBench Mathematics (LiveBench) | 86.8% | 96.8% |
| LiveBench Reasoning (LiveBench) | 86.6% | 92.7% |
| Mystery Game Puzzles (Epoch AI) | 34% | 84% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 94.4% | 100% |
| SimpleQA Verified | 33.6% | 75.6% |
| Terminal-Bench 4.0 (Vals AI) | 18.7% | 59.6% |
| WeirdML (Håvard Tveit Ihle) | 63% | 93.6% |
| LMArena Elo | 1436 | 1477 |
| LMArena WebDev (LMArena) | 1581 | 1788 |
| SimpleBench (SimpleBench) | 61.1% | 86.5% |
Higher is better. Each score links to where it was published.