Claude Fable 5.1 vs GPT-5.2
Claude Fable 5.1 
GPT-5.2 Verdict
- Claude Fable 5.1 (max) leads on quality: 70.3 vs 61.6.
- Claude Fable 5.1 (max) is stronger in agents & tools, coding, composite, human preference, knowledge, maths, reasoning.
- GPT-5.2 is stronger in instruction following, long context, multimodal.
- GPT-5.2 is 4.2× cheaper ($4.81 vs $20.00 per 1M blended).
- GPT-5.2 streams 1.7× faster (68 vs 40 tokens per second).
| Metric | Claude Fable 5.1 (max) | GPT-5.2 |
|---|---|---|
| BenchLeader Index | 70.3 | 61.6 |
| Agents & tools score | 67.4 | 61.2 |
| Coding score | 78.4 | 53.7 |
| Composite score | 76.6 | 67.5 |
| Human preference score | 71.3 | 67.9 |
| Knowledge score | 75.9 | 61.1 |
| Maths score | 77.0 | – |
| Reasoning score | 71.9 | 61.3 |
| Instruction following score | – | 67.4 |
| Long context score | – | 67.9 |
| Multimodal score | – | 59.9 |
| Blended price $/M | $20.00 | $4.81 |
| Output speed | 40 tok/s | 68 tok/s |
| Time to first answer | 299.8 s | 129.4 s |
| Context window | 1M | 400k |
| FrontierMath Tiers 1–3 | 90.2% | – |
| FrontierMath Tier 4 | 87.8% | – |
| OTIS Mock AIME | 100.0% | – |
| SimpleQA Verified | 70.8% | – |
| Humanity's Last Exam | – | 27.8% |
| Terminal-Bench | 57.9% | 64.9% |
| SimpleBench | – | 45.8% |
| SciCode | 62.0% | – |
| Remote Labor Index | – | 2.1% |
| WeirdML | 92.9% | – |
| APEX-Agents | – | 23.0% |
| ProofBench | 100.0% | – |
| Epoch Capabilities Index | – | 153.5 |
| LMArena Text | 1504 | 1476 |
| LMArena Hard Prompts | 1522 | 1497 |
| LMArena Coding | 1517 | 1515 |
| LMArena WebDev | 1764 | 1417 |
| LMArena Vision | – | 1268 |
| LMArena Agent | 14.5 | – |
| LiveBench | 83.4% | – |
| LiveBench Reasoning | 91.7% | – |
| LiveBench Coding | 86.4% | – |
| LiveBench Agentic Coding | 66.1% | – |
| LiveBench Mathematics | 97.0% | – |
| LiveBench Data Analysis | 80.3% | – |
| LiveBench Language | 89.5% | – |
| AA Intelligence Index | – | 30.4 |
| IFBench | – | 75.4% |
| AA-LCR | – | 82.7% |
| AA-Omniscience | – | -0.9 |
| Terminal-Bench Hard | – | 47.0% |
| GPQA Diamond (AA) | – | 90.3% |
| Humanity's Last Exam (AA) | – | 37.7% |
| τ²-Bench Telecom (AA) | – | 84.8% |
| SWE-Bench Pro | – | 29.9% |
| VISTA | – | 46.6% |
| MultiNRC | – | 42.2% |
| TutorBench | – | 53.5% |
| Kagi LLM Benchmark | – | 73.3% |
| SWE-bench Verified (bash only) | – | 69.0% |
| ARC-AGI-1 | 97.5% | 94.5% |
| ARC-AGI-2 | 90.0% | 72.9% |
| BFCL Overall | – | 55.9% |
Data as of 2026-09-10. Best configuration of each model; every score links to its source on the model pages.
Claude Fable 5.1 vs GPT-5.2: questions
- Is Claude Fable 5.1 better than GPT-5.2?
- Claude Fable 5.1 (max) leads on quality: 70.3 vs 61.6. The BenchLeader Index combines every independent quality benchmark; Claude Fable 5.1 (max) is ahead overall as of 2026-09-10, but check the category scores for your use.
- Is Claude Fable 5.1 better than GPT-5.2 for coding?
- Claude Fable 5.1 scores higher in coding (78 vs 54 on the category index, where 50 is average).
- Is Claude Fable 5.1 better than GPT-5.2 for agentic tasks?
- Claude Fable 5.1 scores higher in agentic tasks (67 vs 61 on the category index, where 50 is average).
- Which is cheaper, Claude Fable 5.1 or GPT-5.2?
- GPT-5.2 is cheaper: $4.81 against $20.00 per million tokens, blended at three input tokens per output token.
- Which is faster, Claude Fable 5.1 or GPT-5.2?
- GPT-5.2 streams faster: 68 against 40 output tokens per second.
- Which has the larger context window?
- Claude Fable 5.1 accepts more context: 1M against 400k tokens.