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

Claude Opus 4 vs Qwen3.5 4B

20 SHARED BENCHMARKS

Across 20 shared benchmarks, Claude Opus 4 scores higher on 15 and Qwen3.5 4B on 5. The widest gap is HMMT 2025, where Qwen3.5 4B scores 76.8 against 15.9. Qwen3.5 4B is the cheaper of the two on tracked API pricing ($0.03 against $15.00 per million input tokens).

ANTHROPICVSALIBABA20 SHARED15–5 HEAD-TO-HEAD

BenchmarkClaude Opus 4MARGINQwen3.5 4B

AA Intelligence2520

AA-LCR69.363

Artificial Analysis Coding Index3422.6

GPQA Diamond79.677.1

HLE12.39.9

HMMT 202515.976.8

IFBench53.759.2

ifeval87.489.8

LiveCodeBench v647.455.8

longbench_v255.650

mmlu_redux94.288.8

MMLU-Pro86.679.1

mmmlu88.876.1

MMMU73.773.4

multichallenge58.649

scicode40.918.3

supergpqa56.552.9

Terminal-Bench Hard31.118.2

τ²-Bench (Retail)81.871.9

τ²-Bench Telecom (AA run)73.492.1

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 Opus 4 withALL PAIRINGS →

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

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 fieldGemini 3.6 Flash Nemotron 3 Super 120B A12B GPT-5.5 Claude Opus 4.8 GPT-4o GPT-5.6 Sol Gemini 3.1 Pro GPT-5.4