Claude Fable 5.1 vs GPT-5.4
Claude Fable 5.1 
GPT-5.4 Verdict
- Claude Fable 5.1 (xhigh) leads on quality: 70.3 vs 63.4.
- Claude Fable 5.1 (xhigh) is stronger in coding, composite, knowledge, long context, reasoning.
- GPT-5.4 is stronger in agents & tools, human preference, instruction following, multimodal.
- GPT-5.4 is 3.6× cheaper ($5.63 vs $20.00 per 1M blended).
- GPT-5.4 streams 2.2× faster (130 vs 58 tokens per second).
| Metric | Claude Fable 5.1 (xhigh) | GPT-5.4 |
|---|---|---|
| BenchLeader Index | 70.3 | 63.4 |
| Coding score | 71.3 | 51.6 |
| Composite score | 95.0 | 78.1 |
| Knowledge score | 84.1 | 66.8 |
| Long context score | 68.1 | 67.6 |
| Reasoning score | 76.4 | 62.3 |
| Agents & tools score | – | 66.1 |
| Human preference score | – | 64.5 |
| Instruction following score | – | 71.7 |
| Multimodal score | – | 64.0 |
| Blended price $/M | $20.00 | $5.63 |
| Output speed | 58 tok/s | 130 tok/s |
| Time to first answer | 132.0 s | 126.4 s |
| Context window | 1M | 1.1M |
| Humanity's Last Exam | 46.5% | – |
| Terminal-Bench | – | 81.8% |
| SciCode | 60.1% | – |
| APEX-Agents | – | 34.9% |
| Epoch Capabilities Index | – | 156.9 |
| LMArena Text | – | 1466 |
| LMArena Hard Prompts | – | 1488 |
| LMArena Coding | – | 1514 |
| LMArena WebDev | – | 1386 |
| LMArena Vision | – | 1293 |
| AA Intelligence Index | 53.2 | 39.0 |
| IFBench | – | 74.0% |
| AA-LCR | 83.0% | 82.0% |
| MMMU-Pro | – | 78.4% |
| AA-Omniscience | 42.4 | 5.8 |
| Terminal-Bench Hard | – | 57.6% |
| GPQA Diamond (AA) | 93.4% | 92.0% |
| Humanity's Last Exam (AA) | 58.7% | 43.7% |
| SciCode (AA) | 60.9% | – |
| τ²-Bench Telecom (AA) | – | 87.1% |
| HiL-Bench | – | 9.7% |
| EQ-Bench 4 | – | 1272 |
| Kagi LLM Benchmark | – | 63.8% |
| 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.