Which is better, Qwen3.5 2B or Qwen3.8 Max Preview?

Qwen3.5 2B vs Qwen3.8 Max Preview

18 SHARED BENCHMARKS

Across 18 shared benchmarks, Qwen3.5 2B scores higher on 0 and Qwen3.8 Max Preview on 18. The widest gap is HLE, where Qwen3.8 Max Preview scores 43.6 against 5.

ALIBABAVSALIBABA18 SHARED0–18 HEAD-TO-HEAD

BenchmarkQwen3.5 2BMARGINQwen3.8 Max Preview

AA Agentic Index0.849.6

AA Intelligence6.940.3

AA-LCR25.678.3

AA-Omniscience-60.23.4

Artificial Analysis Coding Index2.971.8

critpt020

gdpval056.5

GPQA Diamond51.692.7

HLE543.6

IFBench41.382.8

longbench_v238.766.3

MMMU-Pro4382.3

OmniScience Accuracy8.131.9

OmniScience Non-Hallucination25.858.3

RealWorldQA65.188

scicode7.253.2

TauBench V3 - Banking2.551.3

Terminal-Bench 2.1386.6

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

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