Which is better, Qwen3.5 2B or Qwen3.6 27B?

Qwen3.5 2B vs Qwen3.6 27B

28 SHARED BENCHMARKS

Across 28 shared benchmarks, Qwen3.5 2B scores higher on 0 and Qwen3.6 27B on 28. The widest gap is Terminal-Bench Hard, where Qwen3.6 27B scores 34.8 against 3.8.

ALIBABAVSALIBABA28 SHARED0–28 HEAD-TO-HEAD

BenchmarkQwen3.5 2BMARGINQwen3.6 27B

AA Agentic Index0.823.6

AA Intelligence6.937

AA-LCR25.677.3

AA-Omniscience-60.2-20

Artificial Analysis Coding Index2.953.7

C-Eval73.291.4

critpt01.1

gdpval028.4

GPQA Diamond51.687.8

HLE524

IFBench41.369.1

MathVista48.787.4

mmlu_redux79.693.5

MMLU-Pro66.586.2

MMMU-Pro4375.8

MMStar55.181.4

OCRBench86.189.4

OmniScience Accuracy8.119.6

OmniScience Non-Hallucination25.850.7

RealWorldQA65.184.1

scicode7.242.8

SimpleVQA35.256.1

supergpqa37.566

TauBench V3 - Banking2.516.7

Terminal-Bench 2.1360.7

Terminal-Bench Hard3.834.8

τ²-Bench Telecom (AA run)81.694.2

τ³-Bench6.215.3

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 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 fieldQwen3.7 Max Qwen3.8 Max Preview Qwen3.7 Plus Preview Claude Opus 4 Qwen3.5 4B Gemini 3.6 Flash Nemotron 3 Super 120B A12B GPT-5.5

Compare Qwen3.6 27B 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 fieldQwen3.7 Max Qwen3.8 Max Preview Qwen3.7 Plus Preview Claude Opus 4 Qwen3.5 4B Gemini 3.6 Flash Nemotron 3 Super 120B A12B GPT-5.5