Modelle vergleichen
A metric-by-metric comparison using the latest available benchmark, runtime, and pricing values. Tie wins more comparable metrics.
| Metric | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) | Gemini 3.5 Flash (high) |
|---|---|---|
| Artificial Analysis Intelligence Index | 59,9 | 50,2 |
| Artificial Analysis Coding Index | 76,5 | 70,1 |
| LiveBench Mathematics | 96% | 88,2% |
| GPQA | 92,6% | 92,2% |
| Humanity's Last Exam | 53,3% | 41% |
| SciCode | 60,2% | 53,1% |
| Output Speed | 69,4 tok/s | 241,2 tok/s |
| Time to First Token | 83,88 s | 10,42 s |
| Blended Price | 20,00 $ / 1M | 3,38 $ / 1M |
| Input Price | 10,00 $ / 1M | 1,50 $ / 1M |
| Output Price | 50,00 $ / 1M | 9,00 $ / 1M |
| Value Index | 3 | 14,87 |
