Refresh Models —Deals —Regulatory —Sources —

Qwen3.5 2B vs Qwen3.7 Max

27 SHARED BENCHMARKS

Across 27 shared benchmarks, Qwen3.5 2B scores higher on 0 and Qwen3.7 Max on 27. The widest gap is HLE, where Qwen3.7 Max scores 41.4 against 5.

ALIBABAVSALIBABA27 SHARED0–27 HEAD-TO-HEAD

BenchmarkQwen3.5 2BMARGINQwen3.7 Max

AA Agentic Index0.823.9

AA Intelligence6.929.9

AA-LCR25.679

AA-Omniscience-60.213.5

Artificial Analysis Coding Index2.966

GPQA Diamond51.692.4

HLE541.4

IFBench41.380.5

ifeval78.694.3

include55.486.2

longbench_v238.765.3

mmlu_prox52.387

mmlu_redux79.695

MMLU-Pro66.589.6

mmmlu63.190.3

OmniScience Accuracy8.131.1

OmniScience Non-Hallucination25.874.4

scicode7.253.5

supergpqa37.573.6

TauBench V3 - Banking2.511.8

Terminal-Bench 2.1375

Terminal-Bench Hard3.850.8

τ²-Bench Telecom (AA run)81.694.7

τ³-Bench6.210.9

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 fieldQwen3.8 Max Preview Qwen3.7 Plus Preview Claude Opus 4 Qwen3.5 4B Gemini 3.6 Flash Nemotron 3 Super 120B A12B GPT-5.5 Claude Opus 4.8

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