Compare Models
A metric-by-metric comparison using the latest available benchmark, runtime, and pricing values. Grok 4.5 (high) wins more comparable metrics.
| Metric | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) | Grok 4.5 (high) |
|---|---|---|
| Artificial Analysis Intelligence Index | 59.9 | 53.8 |
| Artificial Analysis Coding Index | 76.5 | 72.4 |
| LiveBench Mathematics | 96% | 90.8% |
| GPQA | 92.6% | 93.1% |
| Humanity's Last Exam | 53.3% | 40.3% |
| SciCode | 60.2% | 54.1% |
| Output Speed | 69.4 tok/s | 122.8 tok/s |
| Time to First Token | 83.88 s | 11.63 s |
| Blended Price | $20.00 / 1M | $3.00 / 1M |
| Input Price | $10.00 / 1M | $2.00 / 1M |
| Output Price | $50.00 / 1M | $6.00 / 1M |
| Value Index | 3 | 17.93 |
