# Claude Fable 5 vs Qwen3.7 Plus

> Claude Fable 5 is the stronger model overall, scoring 66.3 to 45.0 on the Noometry Index. Qwen3.7 Plus costs 29× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-fable-5-vs-qwen3-7-plus
- Last updated: 2026-10-10
- Shared benchmarks: 31

## Summary

- They share 31 benchmarks with published results for both. Claude Fable 5 scores higher in 10 categories and Qwen3.7 Plus in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Fable 5 leads 88.4 to 49.3.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 87% for Claude Fable 5 and 34.4% for Qwen3.7 Plus.
- Qwen3.7 Plus is cheaper at $0.40 / $1.60 per million input/output tokens, against $10 / $50 for Claude Fable 5.

## Snapshot

| | Claude Fable 5 | Qwen3.7 Plus |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 66.3 | 45.0 |
| Rank | 5 | 66 |
| Context | 1M | 1M |
| Input $/M | $10 | $0.40 |
| Output $/M | $50 | $1.60 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Fable 5: 67.0 (#4)
- Qwen3.7 Plus: 36.1 (#200)

| Benchmark | Claude Fable 5 | Qwen3.7 Plus |
|---|---|---|
| FrontierCode | 53.5% | 10.2% |
| SciCode | 61% | 45.5% |
| LMArena Coding | 1519 | 1473 |
| DeepSWE | 69.9% | — |
| LMArena WebDev | 1626 | — |
| FrontierSWE | 47% | — |
| WeirdML | 91.9% | — |
| MirrorCode | 63.9% | — |
| ALE-Bench | 2,041 | — |

## Agentic & Tool Use

- Claude Fable 5: 54.1 (#2)
- Qwen3.7 Plus: 21.2 (#130)

| Benchmark | Claude Fable 5 | Qwen3.7 Plus |
|---|---|---|
| APEX-Agents | 63.6% | — |
| OSWorld 2.0 | — | 2.8% |
| Remote Labor Index | 16.1% | — |
| τ²-bench Banking | 39.7% | — |
| PostTrainBench | 41.8% | — |
| GBAEval | 74.5% | — |
| GDP.pdf | 30% | — |
| LMArena Search | 1230 | — |
| Vending-Bench 2 | 5,680 | — |

## Reasoning

- Claude Fable 5: 76.8 (#4)
- Qwen3.7 Plus: 38.4 (#54)

| Benchmark | Claude Fable 5 | Qwen3.7 Plus |
|---|---|---|
| NYT Connections (extended) | 92.7% | 74.8% |
| CritPt | 28.6% | 9.1% |
| Chess Puzzles | 41% | 24% |
| LMArena Hard Prompts | 1508 | 1460 |
| Mystery Game Puzzles | 52% | 17% |
| DTBench | 98.4% | 84% |
| LMCA | 61.1% | 37.6% |
| Epoch Capabilities Index | 163.6 | 147.39 |
| ARC-AGI-2 | 89.2% | — |
| SimpleBench | 81.9% | — |
| Kagi LLM Benchmark | 91.4% | — |
| ARC-AGI-1 | 98.5% | — |
| EnigmaEval | 39.3% | — |
| EBR-Bench | 39.5% | — |
| Surface Evolver Bench | 95% | — |
| Bench to the Future 3 | 0.13 | — |

## Math

- Claude Fable 5: 88.4 (#5)
- Qwen3.7 Plus: 49.3 (#47)

| Benchmark | Claude Fable 5 | Qwen3.7 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | 87% | 34.4% |
| OTIS Mock AIME 2024-2025 | 100% | 93.3% |
| LMArena Math | 1519 | 1467 |
| FrontierMath Tier 4 | 90.2% | — |
| ProofBench | 95% | — |
| FrontierMath Erdős | 0% | — |

## Knowledge

- Claude Fable 5: 62.3 (#22)
- Qwen3.7 Plus: 54.9 (#46)

| Benchmark | Claude Fable 5 | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 85.9% | 87.9% |
| LMArena Expert | 1534 | 1467 |
| SimpleQA Verified | 70.7% | — |

## Multimodal

- Claude Fable 5: 45.6 (#14)
- Qwen3.7 Plus: 41.2 (#30)

| Benchmark | Claude Fable 5 | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | 1326 | 1281 |
| LMArena Document | 1496 | 1444 |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 35.8% | — |

## Multilingual

- Claude Fable 5: 57.6 (#8)
- Qwen3.7 Plus: 55.0 (#36)

| Benchmark | Claude Fable 5 | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1483 | 1445 |
| LMArena Chinese | 1546 | 1510 |
| LMArena French | 1509 | 1471 |
| LMArena German | 1486 | 1471 |
| LMArena Japanese | 1507 | 1411 |
| LMArena Korean | 1493 | 1416 |
| LMArena Russian | 1507 | 1457 |
| LMArena Spanish | 1503 | 1453 |

## Instruction Following

- Claude Fable 5: 78.8 (#7)
- Qwen3.7 Plus: 75.9 (#49)

| Benchmark | Claude Fable 5 | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1503 | 1439 |

## Long Context

- Claude Fable 5: 46.3 (#22)
- Qwen3.7 Plus: 44.5 (#61)

| Benchmark | Claude Fable 5 | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1510 | 1454 |

## Writing & Preference

- Claude Fable 5: 76.1 (#5)
- Qwen3.7 Plus: 64.5 (#54)

| Benchmark | Claude Fable 5 | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1491 | 1454 |
| LMArena Creative Writing | 1494 | 1439 |
| LMArena Multi-Turn | 1505 | 1459 |
| EQ-Bench Creative Writing | 1943 | — |
| EQ-Bench 4 | 1340 | — |

## FAQ

### Is Claude Fable 5 better than Qwen3.7 Plus?

Claude Fable 5 is the stronger model overall, scoring 66.3 to 45.0 on the Noometry Index. Qwen3.7 Plus costs 29× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.

### Which is cheaper, Claude Fable 5 or Qwen3.7 Plus?

Qwen3.7 Plus is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; Claude Fable 5 lists at $10 and $50.

### Is Claude Fable 5 or Qwen3.7 Plus better for coding?

Claude Fable 5 scores higher on coding benchmarks: 67.0 versus 36.1 in the Noometry coding category.

### Which has the bigger context window?

Both accept 1M tokens.

### How many benchmarks do Claude Fable 5 and Qwen3.7 Plus share?

31 benchmarks have published results for both models. Claude Fable 5 has 61 scored results on Noometry and Qwen3.7 Plus has 32.