Claude Fable 5.1 vs Gemini 3.5 Flash
Claude Fable 5.1 
Gemini 3.5 Flash Verdict
- Claude Fable 5.1 (xhigh) leads on quality: 70.3 vs 63.9.
- Claude Fable 5.1 (xhigh) is stronger in coding, composite, knowledge, long context, reasoning.
- Gemini 3.5 Flash (medium) is stronger in agents & tools, human preference, instruction following, multimodal.
- Gemini 3.5 Flash (medium) is 5.9× cheaper ($3.38 vs $20.00 per 1M blended).
- Gemini 3.5 Flash (medium) streams 3.6× faster (209 vs 58 tokens per second).
| Metric | Claude Fable 5.1 (xhigh) | Gemini 3.5 Flash (medium) |
|---|---|---|
| BenchLeader Index | 70.3 | 63.9 |
| Coding score | 71.3 | 58.9 |
| Composite score | 95.0 | 71.4 |
| Knowledge score | 84.1 | 73.9 |
| Long context score | 68.1 | 63.6 |
| Reasoning score | 76.4 | 66.8 |
| Agents & tools score | – | 67.8 |
| Human preference score | – | 67.4 |
| Instruction following score | – | 72.2 |
| Multimodal score | – | 67.6 |
| Blended price $/M | $20.00 | $3.38 |
| Output speed | 58 tok/s | 209 tok/s |
| Time to first answer | 132.0 s | 17.0 s |
| Context window | 1M | 1M |
| Humanity's Last Exam | 46.5% | – |
| SciCode | 60.1% | – |
| LMArena Text | – | 1476 |
| LMArena Hard Prompts | – | 1493 |
| LMArena Coding | – | 1503 |
| LMArena WebDev | – | 1491 |
| LMArena Vision | – | 1306 |
| AA Intelligence Index | 53.2 | 33.6 |
| IFBench | – | 74.6% |
| AA-LCR | 83.0% | 74.3% |
| MMMU-Pro | – | 83.9% |
| AA-Omniscience | 42.4 | 20.8 |
| Terminal-Bench Hard | – | 39.4% |
| GPQA Diamond (AA) | 93.4% | 92.1% |
| Humanity's Last Exam (AA) | 58.7% | 41.3% |
| SciCode (AA) | 60.9% | – |
| τ²-Bench Telecom (AA) | – | 95.6% |
| 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.