Compare Models
A metric-by-metric comparison using the latest available benchmark, runtime, and pricing values. Tie wins more comparable metrics.
| Metric | Claude Fable 5 | GPT-6 Astra (max) |
|---|---|---|
| Artificial Analysis Intelligence Index | 59.9 | 52.7 |
| Artificial Analysis Coding Index | 76.5 | 76.9 |
| LiveBench Mathematics | n/a | 96.8% |
| GPQA | n/a | 96.1% |
| Humanity's Last Exam | n/a | 54.7% |
| SciCode | n/a | 56.5% |
| Output Speed | n/a | 54.3 tok/s |
| Time to First Token | n/a | 203.02 s |
| Blended Price | n/a | $20.00 / 1M |
| Input Price | n/a | $10.00 / 1M |
| Output Price | n/a |
| $50.00 / 1M |
| Value Index | n/a | 2.64 |
