Which is better, Qwen3.5 2B or Qwen3.7 Plus Preview?

Qwen3.5 2B vs Qwen3.7 Plus Preview

29 SHARED BENCHMARKS

Across 29 shared benchmarks, Qwen3.5 2B scores higher on 0 and Qwen3.7 Plus Preview on 29. The widest gap is TauBench V3 - Banking, where Qwen3.7 Plus Preview scores 17.9 against 2.5.

ALIBABAVSALIBABA29 SHARED0–29 HEAD-TO-HEAD

BenchmarkQwen3.5 2BMARGINQwen3.7 Plus Preview

AA Agentic Index0.820.8

AA Intelligence6.939

AA-LCR25.673

AA-Omniscience-60.22.4

Artificial Analysis Coding Index2.955.9

bfcl_v443.672.9

critpt09.1

gdpval021.8

GPQA Diamond51.690.3

HLE535.6

IFBench41.379.1

ifeval78.694.6

include55.483

mmlu_prox52.385.4

mmlu_redux79.694.5

MMLU-Pro66.588.5

mmmlu63.189

MMMU-Pro4380.5

OmniScience Accuracy8.122.5

OmniScience Non-Hallucination25.874.5

RealWorldQA65.186.9

scicode7.251.3

SimpleVQA35.281.7

supergpqa37.571.4

TauBench V3 - Banking2.517.9

Terminal-Bench 2.1361

Terminal-Bench Hard3.847

τ²-Bench Telecom (AA run)81.693

τ³-Bench6.217.9

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 fieldClaude Opus 4 Qwen3.5 4B Gemini 3.6 Flash Nemotron 3 Super 120B A12B GPT-5.5 Claude Opus 4.8 GPT-4o GPT-5.6 Sol

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