Which is better, Claude Fable 5 or Qwen3.5 4B?

Claude Fable 5 vs Qwen3.5 4B

20 SHARED BENCHMARKS

Across 20 shared benchmarks, Claude Fable 5 scores higher on 20 and Qwen3.5 4B on 0. The widest gap is gdpval, where Claude Fable 5 scores 56.6 against 8.3. Qwen3.5 4B is the cheaper of the two on tracked API pricing ($0.03 against $10.00 per million input tokens).

ANTHROPICVSALIBABA20 SHARED20–0 HEAD-TO-HEAD

BenchmarkClaude Fable 5MARGINQwen3.5 4B

AA Agentic Index5136.3

AA Intelligence6220

AA-LCR82.363

AA-Omniscience43.3-58.4

Artificial Analysis Coding Index76.522.6

critpt28.60

gdpval56.68.3

GPQA Diamond92.677.1

HLE64.59.9

IFBench63.559.2

MMMU-Pro84.265.4

OmniScience Accuracy65.315.1

OmniScience Non-Hallucination36.413.4

scicode6118.3

TauBench V3 - Banking38.16.8

Terminal-Bench 2.18825.8

Terminal-Bench Hard62.918.2

τ²-Bench Telecom (AA run)98.592.1

τ³-Bench26.88.2

τ³-Bench Banking26.85.5

Best tracked score per model per benchmark (default configuration; source-attributed). ↓ marks lower-is-better metrics. Open either model for its full surface, provenance and pricing. Quoted rates are the price-setter row we currently track for each model — its direct or vendor-official listing where one exists (anthropic-official, direct), otherwise the lowest tracked offer.

Compare Claude Fable 5 withALL PAIRINGS →

AnthropicClaude Opus 4.8 Claude Opus 4.6 Claude Sonnet 4.5 Claude 3.5 Sonnet Claude Opus 4.5 Claude Opus 5

Across the fieldGemini 3.6 Flash Nemotron 3 Super 120B A12B GPT-5.5 GPT-4o GPT-5.6 Sol Gemini 3.1 Pro GPT-5.4 GPT-5.2

Compare Qwen3.5 4B withALL PAIRINGS →

AlibabaQwen3.5 35B A3B Qwen3 VL 4B (Reasoning)Qwen3.5 397B A17B Qwen2.5 Instruct 72B Qwen3.5 27B Qwen3.6 Plus

Across the fieldGPT-5 Claude Opus 4.5 DeepSeek-V4-Pro DeepSeek-V3 Kimi K2.6 Kimi K2.5 o3 GPT-5.1