Claude Fable 5.1 vs GPT-6.1 Sol
Claude Fable 5.1 
GPT-6.1 Sol Verdict
- Claude Fable 5.1 (max) leads on quality: 70.8 vs 69.3.
- Claude Fable 5.1 (max) is stronger in agents & tools, coding, composite, human preference, long context, maths, multimodal, reasoning.
- GPT-6.1 Sol (max) is stronger in knowledge.
- GPT-6.1 Sol (max) is 5.0× cheaper ($4.00 vs $20.00 per 1M blended).
| Metric | Claude Fable 5.1 (max) | GPT-6.1 Sol (max) |
|---|---|---|
| BenchLeader Index | 70.8 | 69.3 |
| Agents & tools score | 70.1 | 63.9 |
| Coding score | 75.3 | 72.4 |
| Composite score | 82.5 | 79.0 |
| Human preference score | 70.1 | 68.1 |
| Knowledge score | 77.9 | 78.8 |
| Long context score | 68.0 | 66.8 |
| Maths score | 73.2 | 72.5 |
| Multimodal score | 67.0 | 66.2 |
| Reasoning score | 77.1 | 76.4 |
| Blended price $/M | $20.00 | $4.00 |
| Output speed | 70 tok/s | 56 tok/s |
| Time to first answer | 290.8 s | 326.9 s |
| Context window | 1M | 1.1M |
| GPQA Diamond | – | 95.4% |
| FrontierMath Tiers 1–3 | 90.2% | 93.7% |
| FrontierMath Tier 4 | 87.8% | 100.0% |
| OTIS Mock AIME | 100.0% | 100.0% |
| SimpleQA Verified | 70.8% | 73.9% |
| Terminal-Bench | 57.9% | 58.2% |
| SciCode | 63.1% | 54.2% |
| WeirdML | 92.9% | – |
| APEX-Agents | – | 60.0% |
| ProofBench | 100.0% | – |
| LMArena Text | 1501 | 1484 |
| LMArena Hard Prompts | 1521 | 1507 |
| LMArena Coding | 1534 | 1545 |
| LMArena WebDev | 1744 | 1755 |
| LMArena Vision | 1318 | 1288 |
| LMArena Agent | 12.7 | 11.7 |
| LiveBench | 83.4% | 81.6% |
| LiveBench Reasoning | 91.7% | 92.6% |
| LiveBench Coding | 86.4% | 80.4% |
| LiveBench Agentic Coding | 66.1% | 54.5% |
| LiveBench Mathematics | 97.0% | 96.8% |
| LiveBench Data Analysis | 80.3% | 82.7% |
| LiveBench Language | 89.5% | 90.1% |
| LiveBench Instruction Following | 73.0% | 74.2% |
| AA Intelligence Index v4.3.2 | 53.4 | 51.8 |
| AA-LCR | 85.3% | 83.0% |
| MMMU-Pro | – | 86.0% |
| AA-Omniscience | 43.5 | 41.5 |
| GPQA Diamond (AA) | 93.7% | – |
| Humanity's Last Exam (AA) | 59.1% | 52.9% |
| SciCode (AA) | 63.1% | 54.2% |
| IOI | – | 96.9% |
| Vals Index | – | 61.1 |
| ARC-AGI-1 | 97.5% | 96.5% |
| ARC-AGI-2 | 90.0% | 94.2% |
| ARC-AGI-3 | – | 96.2% |
| CritPt | 29.7% | 31.7% |
| GDPval-AA v2.1 | 62.8% | 53.8% |
| τ³-Banking (AA) | 47.2% | – |
| ITBench SRE (AA) | 49.5% | – |
| Analyst Agent (AA) | 57.5% | 50.0% |
| BioMysteryBench | – | 79.6% |
| Code Migration | – | 65.1% |
| CUA-bench | 13.2% | – |
| CyberBench | – | 39.3% |
| Excel Modeling Benchmark | – | 70.8% |
| Finance Agent v2 | – | 52.0% |
| Harvey's Legal Agent Benchmark | – | 5.4% |
| Legal Research Bench | – | 38.5% |
| MedCode | – | 48.8% |
| MedScribe | – | 86.5% |
| MysteryMechanism | – | 46.4% |
| Public Benefits Bench | – | 59.3% |
| SAGE | – | 46.5% |
| SREBench | – | 50.8% |
| Tax Agent Bench | – | 62.3% |
| Terminal-Bench 4.0 (Vals) | – | 55.0% |
| Vibe Code Bench v1.1 | – | 88.9% |
| LMArena Maths | 1522 | 1488 |
| LMArena Creative Writing | 1483 | 1462 |
| LMArena Instruction Following | 1498 | 1488 |
| LMArena Multi-turn | 1485 | 1487 |
| LMArena Longer Queries | 1509 | 1496 |
| LMArena Document | 1493 | – |
| Chess Puzzles | 47.0% | 61.0% |
| EBR-bench | 57.1% | 54.3% |
| Mystery Game Puzzles | 58.0% | 80.0% |
| CursorBench | 51.8% | – |
| GDP.pdf | 27.6% | – |
| FrontierSWE | 56.3% | – |
| Terminal-Bench 4.0 (AA) | 52.0% | 56.1% |
| Terminal-Bench 2.1 (AA) | 91.4% | – |
| AutomationBench | 59.4% | 64.9% |
| GDP.pdf | 26.2% | 31.0% |
| MLCR | 71.1% | 33.9% |
| Harvey LAB | 6.4% | 6.9% |
| AA-Omniscience: accuracy | 67.2% | 62.1% |
| AA-Omniscience: non-hallucination | 27.4% | 45.7% |
| AA-Briefcase v1.1 | 1675 | 1557 |
Data as of 2026-10-11. Best configuration of each model; every score links to its source on the model pages.
Claude Fable 5.1 vs GPT-6.1 Sol: questions
- Is Claude Fable 5.1 better than GPT-6.1 Sol?
- Claude Fable 5.1 (max) leads on quality: 70.8 vs 69.3. The BenchLeader Index combines every independent quality benchmark; Claude Fable 5.1 (max) is ahead overall as of 2026-10-11, but check the category scores for your use.
- Is Claude Fable 5.1 better than GPT-6.1 Sol for coding?
- Claude Fable 5.1 scores higher in coding (75 vs 72 on the category index, where 50 is average).
- Is Claude Fable 5.1 better than GPT-6.1 Sol for agentic tasks?
- Claude Fable 5.1 scores higher in agentic tasks (70 vs 64 on the category index, where 50 is average).
- Which is cheaper, Claude Fable 5.1 or GPT-6.1 Sol?
- GPT-6.1 Sol is cheaper: $4.00 against $20.00 per million tokens, blended at three input tokens per output token.
- Which is faster, Claude Fable 5.1 or GPT-6.1 Sol?
- Claude Fable 5.1 streams faster: 70 against 56 output tokens per second.
- Which has the larger context window?
- GPT-6.1 Sol accepts more context: 1.1M against 1M tokens.