Claude Fable 5.1 vs Gemini 3.8 Flash
Claude Fable 5.1 
Gemini 3.8 Flash Verdict
- Claude Fable 5.1 (xhigh) leads on quality: 70.3 vs 63.5.
- Claude Fable 5.1 (xhigh) is stronger in coding, composite, knowledge, reasoning.
- Gemini 3.8 Flash (medium) is stronger in long context, multimodal.
- Gemini 3.8 Flash (medium) is 13× cheaper ($1.50 vs $20.00 per 1M blended).
- Gemini 3.8 Flash (medium) streams 4.7× faster (273 vs 58 tokens per second).
| Metric | Claude Fable 5.1 (xhigh) | Gemini 3.8 Flash (medium) |
|---|---|---|
| BenchLeader Index | 70.3 | 63.5 |
| Coding score | 71.3 | 63.6 |
| Composite score | 95.0 | 79.4 |
| Knowledge score | 84.1 | 77.6 |
| Long context score | 68.1 | 68.7 |
| Reasoning score | 76.4 | – |
| Multimodal score | – | 68.9 |
| Blended price $/M | $20.00 | $1.50 |
| Output speed | 58 tok/s | 273 tok/s |
| Time to first answer | 132.0 s | 13.8 s |
| Context window | 1M | 1M |
| Humanity's Last Exam | 46.5% | – |
| SciCode | 60.1% | 54.4% |
| AA Intelligence Index | 53.2 | 40 |
| AA-LCR | 83.0% | 84.0% |
| MMMU-Pro | – | 84.2% |
| AA-Omniscience | 42.4 | 28.6 |
| GPQA Diamond (AA) | 93.4% | 93.5% |
| Humanity's Last Exam (AA) | 58.7% | 42.1% |
| SciCode (AA) | 60.9% | 55.1% |
| ARC-AGI-1 | 96.5% | – |
| ARC-AGI-2 | 90.0% | – |
Data as of 2026-09-09. Best configuration of each model; every score links to its source on the model pages.