Claude Fable 5.1 vs GPT-6 Astra
Claude Fable 5.1 
GPT-6 Astra Verdict
- Claude Fable 5.1 (xhigh) and GPT-6 Astra (max) are level on quality (70.3 vs 70.6).
- Claude Fable 5.1 (xhigh) is stronger in composite, knowledge, long context, reasoning.
- GPT-6 Astra (max) is stronger in coding, agents & tools, maths.
- They cost about the same ($20.00 per 1M blended).
| Metric | Claude Fable 5.1 (xhigh) | GPT-6 Astra (max) |
|---|---|---|
| BenchLeader Index | 70.3 | 70.6 |
| Coding score | 71.3 | 79.0 |
| Composite score | 95.0 | 73.1 |
| Knowledge score | 84.1 | 79.8 |
| Long context score | 68.1 | – |
| Reasoning score | 76.4 | 70.9 |
| Agents & tools score | – | 68.2 |
| Maths score | – | 77.0 |
| Blended price $/M | $20.00 | $22.00 |
| Output speed | 58 tok/s | 54 tok/s |
| Time to first answer | 132.0 s | 328.6 s |
| Context window | 1M | 1.1M |
| GPQA Diamond | – | 95.8% |
| FrontierMath Tiers 1–3 | – | 93.7% |
| FrontierMath Tier 4 | – | 97.6% |
| OTIS Mock AIME | – | 100.0% |
| SimpleQA Verified | – | 75.6% |
| Humanity's Last Exam | 46.5% | – |
| Terminal-Bench | – | 58.2% |
| SciCode | 60.1% | 56.5% |
| FrontierCode | – | 53.3% |
| LMArena WebDev | – | 1796 |
| LMArena Agent | – | 12.5 |
| LiveBench | – | 82.2% |
| LiveBench Reasoning | – | 92.7% |
| LiveBench Coding | – | 80.4% |
| LiveBench Agentic Coding | – | 57.3% |
| LiveBench Mathematics | – | 96.8% |
| LiveBench Data Analysis | – | 83.0% |
| LiveBench Language | – | 89.4% |
| AA Intelligence Index | 53.2 | – |
| AA-LCR | 83.0% | – |
| AA-Omniscience | 42.4 | – |
| GPQA Diamond (AA) | 93.4% | – |
| Humanity's Last Exam (AA) | 58.7% | – |
| SciCode (AA) | 60.9% | – |
| Terminal-Bench 2.1 (Vals) | – | 87.3% |
| Vals Index | – | 66.6 |
| ARC-AGI-1 | 96.5% | 97.5% |
| ARC-AGI-2 | 90.0% | 95.0% |
| ARC-AGI-3 | – | 62.7% |
Data as of 2026-09-09. Best configuration of each model; every score links to its source on the model pages.