Model comparison
Claude Fable 5.1 vs Qwen3.5 397B-A17B
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 46.0 on the Noometry Index. Qwen3.5 397B-A17B costs 15× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.
Last verified . 29 shared benchmarks.
Alibaba (Qwen)Summary
- They share 29 benchmarks with published results for both. Claude Fable 5.1 scores higher in 10 categories and Qwen3.5 397B-A17B in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Fable 5.1 leads 89.6 to 46.1.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 90.2% for Claude Fable 5.1 and 31.2% for Qwen3.5 397B-A17B.
- Qwen3.5 397B-A17B is cheaper at $0.60 / $3.60 per million input/output tokens, against $10 / $50 for Claude Fable 5.1.
- Claude Fable 5.1 accepts more context: 1M tokens versus 262K.
- Qwen3.5 397B-A17B has downloadable open weights; the other is API-only.
Side by side
| Claude Fable 5.1 | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 69.0 | 46.0 |
| Released | 2026-09-01 | 2026-02-01 |
| Weights | Proprietary | Open |
| Context window | 1M | 262K |
| Max output | 128K | 66K |
| Input $ / M tokens | $10 | $0.60 |
| Output $ / M tokens | $50 | $3.60 |
| Results tracked | 52 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Fable 5.1 leads
Claude Fable 5.1: 74.7 (#1), Qwen3.5 397B-A17B: 42.0 (#114)
| Benchmark | Claude Fable 5.1 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena WebDev | 1744 | 1400 |
| LMArena Coding | 1528 | 1465 |
| FrontierCode | 50.9% | — |
| CursorBench | 51.8% | — |
| FrontierSWE | 56.3% | — |
| SciCode | 63.1% | — |
| GSO | 88.2% | — |
| WeirdML | 92.9% | — |
| MirrorCode | 73.3% | — |
| ALE-Bench | 2,143 | — |
Agentic & Tool Use Claude Fable 5.1 leads
Claude Fable 5.1: 50.7 (#5), Qwen3.5 397B-A17B: 33.3 (#53)
| Benchmark | Claude Fable 5.1 | Qwen3.5 397B-A17B |
|---|---|---|
| APEX-Agents | 68.6% | 24.9% |
| Remote Labor Index | 17.9% | — |
| τ²-bench Airline | — | 81.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 84.4% |
| τ²-bench Telecom | — | 97.8% |
| GDP.pdf | 29.6% | — |
| Vending-Bench 2 | 5,422 | — |
Reasoning Claude Fable 5.1 leads
Claude Fable 5.1: 76.7 (#7), Qwen3.5 397B-A17B: 34.5 (#70)
| Benchmark | Claude Fable 5.1 | Qwen3.5 397B-A17B |
|---|---|---|
| NYT Connections (extended) | 90% | 58.9% |
| Chess Puzzles | 47% | 13% |
| LMArena Hard Prompts | 1526 | 1448 |
| Mystery Game Puzzles | 58% | 18% |
| DTBench | 97.6% | 87.5% |
| LMCA | 65.5% | 37.9% |
| Epoch Capabilities Index | 164.7 | 146.65 |
| ARC-AGI-2 | 90% | — |
| Kagi LLM Benchmark | — | 73.7% |
| ARC-AGI-1 | 97.5% | — |
| CritPt | 31.1% | — |
| Thematic Generalization | — | 65.1% |
| EBR-Bench | 57.1% | — |
Math Claude Fable 5.1 leads
Claude Fable 5.1: 89.6 (#4), Qwen3.5 397B-A17B: 46.1 (#73)
| Benchmark | Claude Fable 5.1 | Qwen3.5 397B-A17B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 90.2% | 31.2% |
| OTIS Mock AIME 2024-2025 | 100% | 88.9% |
| LMArena Math | 1525 | 1454 |
| FrontierMath Tier 4 | 87.8% | — |
| ProofBench | 100% | — |
| FrontierMath Erdős | 0% | — |
Knowledge Claude Fable 5.1 leads
Claude Fable 5.1: 69.6 (#6), Qwen3.5 397B-A17B: 53.3 (#58)
| Benchmark | Claude Fable 5.1 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Expert | 1535 | 1462 |
| GPQA Diamond | — | 86.4% |
| Humanity's Last Exam | 46.5% | — |
| SimpleQA Verified | 70.8% | — |
Multimodal Claude Fable 5.1 leads
Claude Fable 5.1: 53.9 (#4), Qwen3.5 397B-A17B: 40.7 (#44)
| Benchmark | Claude Fable 5.1 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | 1318 | 1263 |
| Blueprint-Bench 2 | 41.9% | — |
| Furniture Assembly | 70% | — |
| LMArena Document | 1513 | — |
Multilingual Claude Fable 5.1 leads
Claude Fable 5.1: 59.1 (#3), Qwen3.5 397B-A17B: 53.7 (#59)
| Benchmark | Claude Fable 5.1 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | 1507 | 1430 |
| LMArena Chinese | 1586 | 1500 |
| LMArena French | 1525 | 1461 |
| LMArena German | 1500 | 1447 |
| LMArena Japanese | 1543 | 1426 |
| LMArena Korean | 1534 | 1384 |
| LMArena Russian | 1521 | 1429 |
| LMArena Spanish | 1516 | 1441 |
Instruction Following Claude Fable 5.1 leads
Claude Fable 5.1: 79.2 (#6), Qwen3.5 397B-A17B: 75.0 (#77)
| Benchmark | Claude Fable 5.1 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | 1517 | 1424 |
Long Context Claude Fable 5.1 leads
Claude Fable 5.1: 46.7 (#20), Qwen3.5 397B-A17B: 44.1 (#74)
| Benchmark | Claude Fable 5.1 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | 1522 | 1442 |
Writing & Preference Claude Fable 5.1 leads
Claude Fable 5.1: 79.2 (#2), Qwen3.5 397B-A17B: 62.3 (#79)
| Benchmark | Claude Fable 5.1 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | 1510 | 1438 |
| LMArena Creative Writing | 1507 | 1401 |
| EQ-Bench Creative Writing | 2162 | 1478 |
| LMArena Multi-Turn | 1492 | 1446 |
Frequently asked questions
Is Claude Fable 5.1 better than Qwen3.5 397B-A17B?
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 46.0 on the Noometry Index. Qwen3.5 397B-A17B costs 15× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.
Which is cheaper, Claude Fable 5.1 or Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is cheaper. It lists at $0.60 per million input tokens and $3.60 per million output tokens; Claude Fable 5.1 lists at $10 and $50.
Is Claude Fable 5.1 or Qwen3.5 397B-A17B better for coding?
Claude Fable 5.1 scores higher on coding benchmarks: 74.7 versus 42.0 in the Noometry coding category.
Which has the bigger context window?
Claude Fable 5.1 does, with 1M tokens against 262K.
How many benchmarks do Claude Fable 5.1 and Qwen3.5 397B-A17B share?
29 benchmarks have published results for both models. Claude Fable 5.1 has 52 scored results on Noometry and Qwen3.5 397B-A17B has 36.