Claude Fable 5 vs GPT-5.2
Claude Fable 5 
GPT-5.2 Verdict
- Claude Fable 5 leads on quality: 70.5 vs 61.6.
- Claude Fable 5 is stronger in agents & tools, coding, composite, human preference, knowledge, multimodal, reasoning.
- GPT-5.2 is stronger in instruction following, long context.
- GPT-5.2 is 4.2× cheaper ($4.81 vs $20.00 per 1M blended).
| Metric | Claude Fable 5 | GPT-5.2 |
|---|---|---|
| BenchLeader Index | 70.5 | 61.6 |
| Agents & tools score | 74.4 | 61.2 |
| Coding score | 70.5 | 53.7 |
| Composite score | 91.8 | 67.5 |
| Human preference score | 71.6 | 67.9 |
| Instruction following score | 62.9 | 67.4 |
| Knowledge score | 71.4 | 61.1 |
| Long context score | 67.8 | 67.9 |
| Multimodal score | 69.7 | 59.9 |
| Reasoning score | 75.9 | 61.3 |
| Blended price $/M | $20.00 | $4.81 |
| Output speed | 63 tok/s | 68 tok/s |
| Time to first answer | 102.3 s | 129.4 s |
| Context window | 1M | 400k |
| Humanity's Last Exam | – | 27.8% |
| Terminal-Bench | – | 64.9% |
| SimpleBench | – | 45.8% |
| Remote Labor Index | 16.1% | 2.1% |
| APEX-Agents | 45.0% | 23.0% |
| FrontierCode | 53.5% | – |
| Epoch Capabilities Index | 163.4 | 153.5 |
| LMArena Text | 1507 | 1476 |
| LMArena Hard Prompts | 1533 | 1497 |
| LMArena Coding | 1551 | 1515 |
| LMArena WebDev | 1628 | 1417 |
| LMArena Vision | 1330 | 1268 |
| AA Intelligence Index | 49.7 | 30.4 |
| IFBench | 63.5% | 75.4% |
| AA-LCR | 82.3% | 82.7% |
| AA-Omniscience | 43.3 | -0.9 |
| Terminal-Bench Hard | 62.9% | 47.0% |
| GPQA Diamond (AA) | 92.6% | 90.3% |
| Humanity's Last Exam (AA) | 55.5% | 37.7% |
| SciCode (AA) | 61.0% | – |
| τ²-Bench Telecom (AA) | 98.5% | 84.8% |
| LiveCodeBench | 89.8% | – |
| MMLU-Pro | 91.5% | – |
| IOI | 72.3% | – |
| LegalBench | 88.6% | – |
| CorpFin | 71.8% | – |
| TaxEval | 76.9% | – |
| Terminal-Bench 2.1 (Vals) | 80.5% | – |
| SWE-bench (Vals) | 95.0% | – |
| GPQA Diamond (Vals) | 93.2% | – |
| Vals Index | 66.0 | – |
| SWE-Bench Pro | – | 29.9% |
| MCP Atlas | 83.3% | – |
| PRBench Finance | 53.9% | – |
| PRBench Legal | 52.6% | – |
| VISTA | – | 46.6% |
| MultiNRC | – | 42.2% |
| HiL-Bench | 56.3% | – |
| TutorBench | – | 53.5% |
| EQ-Bench 4 | 1340 | – |
| Kagi LLM Benchmark | 88.8% | 73.3% |
| SWE-bench Verified (bash only) | – | 69.0% |
| ARC-AGI-1 | – | 94.5% |
| ARC-AGI-2 | – | 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 vs GPT-5.2: questions
- Is Claude Fable 5 better than GPT-5.2?
- Claude Fable 5 leads on quality: 70.5 vs 61.6. The BenchLeader Index combines every independent quality benchmark; Claude Fable 5 is ahead overall as of 2026-09-10, but check the category scores for your use.
- Is Claude Fable 5 better than GPT-5.2 for coding?
- Claude Fable 5 scores higher in coding (71 vs 54 on the category index, where 50 is average).
- Is Claude Fable 5 better than GPT-5.2 for agentic tasks?
- Claude Fable 5 scores higher in agentic tasks (74 vs 61 on the category index, where 50 is average).
- Which is cheaper, Claude Fable 5 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 or GPT-5.2?
- GPT-5.2 streams faster: 68 against 63 output tokens per second.
- Which has the larger context window?
- Claude Fable 5 accepts more context: 1M against 400k tokens.