Claude Fable 5.1 vs Qwen3.6 Plus
Claude Fable 5.1 
Qwen3.6 Plus Verdict
- Claude Fable 5.1 (max) leads on quality: 70.3 vs 59.2.
- Claude Fable 5.1 (max) is stronger in agents & tools, coding, composite, human preference, knowledge, maths, reasoning.
- Qwen3.6 Plus is stronger in instruction following, long context, multimodal.
- Qwen3.6 Plus is 18× cheaper ($1.13 vs $20.00 per 1M blended).
- Qwen3.6 Plus streams 1.4× faster (56 vs 40 tokens per second).
| Metric | Claude Fable 5.1 (max) | Qwen3.6 Plus |
|---|---|---|
| BenchLeader Index | 70.3 | 59.2 |
| Agents & tools score | 67.4 | 57.0 |
| Coding score | 78.4 | 52.8 |
| Composite score | 76.6 | 48.3 |
| Human preference score | 71.3 | 63.9 |
| Knowledge score | 75.9 | 59.0 |
| Maths score | 77.0 | 56.7 |
| Reasoning score | 71.9 | 64.3 |
| Instruction following score | – | 73.0 |
| Long context score | – | 65.7 |
| Multimodal score | – | 62.4 |
| Blended price $/M | $20.00 | $1.13 |
| Output speed | 40 tok/s | 56 tok/s |
| Time to first answer | 299.8 s | 101.1 s |
| Context window | 1M | 1M |
| GPQA Diamond | – | 88.4% |
| FrontierMath Tiers 1–3 | 90.2% | 38.3% |
| FrontierMath Tier 4 | 87.8% | – |
| OTIS Mock AIME | 100.0% | 93.3% |
| SWE-bench Verified (Epoch) | – | 57.9% |
| SimpleQA Verified | 70.8% | 44.1% |
| Terminal-Bench | 57.9% | – |
| SciCode | 62.0% | 40.7% |
| WeirdML | 92.9% | – |
| ProofBench | 100.0% | – |
| Epoch Capabilities Index | – | 147.7 |
| LMArena Text | 1504 | 1444 |
| LMArena Hard Prompts | 1522 | 1468 |
| LMArena Coding | 1517 | 1495 |
| LMArena WebDev | 1764 | 1460 |
| LMArena Agent | 14.5 | – |
| LiveBench | 83.4% | 68.9% |
| LiveBench Reasoning | 91.7% | 75.8% |
| LiveBench Coding | 86.4% | 78.2% |
| LiveBench Agentic Coding | 66.1% | 41.4% |
| LiveBench Mathematics | 97.0% | 83.7% |
| LiveBench Data Analysis | 80.3% | 69.9% |
| LiveBench Language | 89.5% | 75.0% |
| AA Intelligence Index | – | 27.0 |
| IFBench | – | 75.2% |
| AA-LCR | – | 78.3% |
| MMMU-Pro | – | 78.0% |
| AA-Omniscience | – | 0.9 |
| Terminal-Bench Hard | – | 43.9% |
| GPQA Diamond (AA) | – | 88.2% |
| Humanity's Last Exam (AA) | – | 27.9% |
| τ²-Bench Telecom (AA) | – | 97.7% |
| AIME (Vals) | – | 94.6% |
| LiveCodeBench | – | 86.0% |
| MMLU-Pro | – | 87.7% |
| LegalBench | – | 84.2% |
| CorpFin | – | 61.9% |
| TaxEval | – | 74.7% |
| Terminal-Bench 2.1 (Vals) | – | 53.2% |
| SWE-bench (Vals) | – | 73.4% |
| GPQA Diamond (Vals) | – | 87.4% |
| Vals Index | – | 32.0 |
| ARC-AGI-1 | 97.5% | – |
| ARC-AGI-2 | 90.0% | – |
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 Qwen3.6 Plus: questions
- Is Claude Fable 5.1 better than Qwen3.6 Plus?
- Claude Fable 5.1 (max) leads on quality: 70.3 vs 59.2. 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 Qwen3.6 Plus for coding?
- Claude Fable 5.1 scores higher in coding (78 vs 53 on the category index, where 50 is average).
- Is Claude Fable 5.1 better than Qwen3.6 Plus for agentic tasks?
- Claude Fable 5.1 scores higher in agentic tasks (67 vs 57 on the category index, where 50 is average).
- Which is cheaper, Claude Fable 5.1 or Qwen3.6 Plus?
- Qwen3.6 Plus is cheaper: $1.13 against $20.00 per million tokens, blended at three input tokens per output token.
- Which is faster, Claude Fable 5.1 or Qwen3.6 Plus?
- Qwen3.6 Plus streams faster: 56 against 40 output tokens per second.
- Which has the larger context window?
- Both accept 1M tokens of context.