Side by side
| Claude Fable 5.2 | GPT-6.1 Sol | |
|---|---|---|
| Lab | Anthropic | OpenAI |
| Listed | Nov 9, 2026 | Sep 29, 2026 |
| Input per 1M tokens | $12.00 | $3.00 |
| Output per 1M tokens | $60.00 | $15.00 |
| Cached input per 1M | $0.30 | $0.15 |
| Blended (3:1) per 1M | $24.00 | $6.00 |
| Context window | 1M | 1.1M |
| Max output | 128K | 128K |
| Knowledge cutoff | - | - |
| Intelligence index | 64.6 | 54.6 |
| Coding index | - | - |
| Reasoning | Yes | Yes |
| Reads images | Yes | Yes |
| Tool use | Yes | Yes |
| Structured output | Yes | Yes |
Every benchmark both are scored on
Each model's best score per benchmark, with its source. Scores from different sources or settings are not always comparable; each links to where it was published.
| Benchmark | Claude Fable 5.2 | GPT-6.1 Sol | Leader |
|---|---|---|---|
| AIME | 99.7%Epoch AI | 100%Epoch AI | GPT-6.1 Sol |
| ARC-AGI-1 | 98.5%Epoch AI | 98.5%Epoch AI | Tie |
| ARC-AGI-2 | 93.8%Epoch AI | 94.2%Epoch AI | GPT-6.1 Sol |
| Artificial Analysis Intelligence Index | 64.6Artificial Analysis and OpenRouter | 54.6Artificial Analysis and OpenRouter | Claude Fable 5.2 |
| Chess Puzzles | 79%Epoch AI | 68%Epoch AI | Claude Fable 5.2 |
| Earthborne Rangers (EBR-bench) | 90.5Epoch AI | 54.3Epoch AI | Claude Fable 5.2 |
| FrontierMath Tier 4 (v2) | 100%Epoch AI | 100%Epoch AI | Tie |
| FrontierMath Tiers 1-3 (v2) | 95.1%Epoch AI | 93.7%Epoch AI | Claude Fable 5.2 |
| GPQA Diamond | 94.9%Artificial Analysis and OpenRouter | 94.4%Artificial Analysis and OpenRouter | Claude Fable 5.2 |
| Mystery Game Puzzles | 90%Epoch AI | 80%Epoch AI | Claude Fable 5.2 |
| ProofBench | 100%Epoch AI | 99%Epoch AI | Claude Fable 5.2 |
| SimpleQA Verified | 94%Epoch AI | 73.9%Epoch AI | Claude Fable 5.2 |
| tau-bench (Airline) | 68%Artificial Analysis and OpenRouter | 70%Artificial Analysis and OpenRouter | GPT-6.1 Sol |
More comparisons
Where these figures come from
Prices are GenMagic's own, what the studio and the API charge, recomputed from each provider's price list every few minutes. The indices are the Artificial Analysis indices, and every benchmark score links to its source, re-read daily. Measured speed is GenMagic's own generation records, in aggregate. See Anthropic models, OpenAI models, every LLM's price and our sources.