Which is better, Claude 3.5 Sonnet or Qwen3.5 2B?

Claude 3.5 Sonnet vs Qwen3.5 2B

22 SHARED BENCHMARKS

Across 22 shared benchmarks, Claude 3.5 Sonnet scores higher on 15 and Qwen3.5 2B on 7. The widest gap is scicode, where Claude 3.5 Sonnet scores 36.6 against 7.2.

ANTHROPICVSALIBABA22 SHARED15–7 HEAD-TO-HEAD

BenchmarkClaude 3.5 SonnetMARGINQwen3.5 2B

AA Intelligence106.9

AIME 20241617

AIME 20257.419

Artificial Analysis Coding Index30.22.9

BLINK56.548.6

C-Eval76.773.2

GPQA Diamond67.251.6

HLE3.95

ifeval90.178.6

longbench_v24138.7

math_500_em78.381.5

MathVista67.748.7

mmlu_redux88.979.6

MMLU-Pro7866.5

MMMU (val) (Pass@1)68.344.1

MMMU-Pro54.743

MMStar62.255.1

OCRBench7986.1

RealWorldQA60.165.1

scicode36.67.2

supergpqa48.237.5

TextVQA-val70.577.3

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.

Compare Claude 3.5 Sonnet withALL PAIRINGS →

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

Across the fieldQwen3.6 27B Qwen3.7 Max Qwen3.8 Max Preview Qwen3.7 Plus Preview Claude Opus 4 Qwen3.5 4B Gemini 3.6 Flash Nemotron 3 Super 120B A12B

Compare Qwen3.5 2B 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 Pro Claude Fable 5 GPT-5 Claude Opus 4.5 DeepSeek-V4-Pro DeepSeek-V3 Kimi K2.6 Kimi K2.5