Refresh Models —Deals —Regulatory —Sources —

GLM-5.2 vs Qwen3.5 2B

19 SHARED BENCHMARKS

Across 19 shared benchmarks, GLM-5.2 scores higher on 19 and Qwen3.5 2B on 0. The widest gap is AA Intelligence, where GLM-5.2 scores 51 against 6.9.

Z.AIVSALIBABA19 SHARED19–0 HEAD-TO-HEAD

BenchmarkGLM-5.2MARGINQwen3.5 2B

AA Agentic Index39.40.8

AA Intelligence516.9

AA-LCR78.325.6

AA-Omniscience4.4-60.2

Artificial Analysis Coding Index68.82.9

Global-MMLU-Lite89.264.5

GPQA Diamond91.251.6

HLE54.75

IFBench73.341.3

OmniScience Accuracy24.38.1

OmniScience Non-Hallucination73.725.8

scicode51.27.2

TauBench V3 - Banking34.62.5

Terminal-Bench 2.182.73

Terminal-Bench Hard50.83.8

τ²-Bench Telecom (AA run)99.181.6

τ³-Bench26.86.2

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 GLM-5.2 withALL PAIRINGS →

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 fieldo4-mini Claude Sonnet 4.6 o1 Gemma 4 31B Kimi K2 Instruct Gemma 4 E2B GPT-4o mini Qwen3.6 35B A3B