Which is better, GLM-5.2 or Qwen3.5 4B?

GLM-5.2 vs Qwen3.5 4B

22 SHARED BENCHMARKS

Across 22 shared benchmarks, GLM-5.2 scores higher on 22 and Qwen3.5 4B on 0. The widest gap is gdpval, where GLM-5.2 scores 45.9 against 8.3. Qwen3.5 4B is the cheaper of the two on tracked API pricing ($0.03 against $1.40 per million input tokens).

Z.AIVSALIBABA22 SHARED22–0 HEAD-TO-HEAD

BenchmarkGLM-5.2MARGINQwen3.5 4B

AA Agentic Index39.436.3

AA Intelligence5120

AA-LCR78.363

AA-Omniscience4.4-58.4

aime_202699.299

Artificial Analysis Coding Index68.822.6

critpt20.90

gdpval45.98.3

GPQA Diamond91.277.1

HLE54.79.9

HMMT 202594.476.8

hmmt_feb_202692.584.1

IFBench73.359.2

OmniScience Accuracy24.315.1

OmniScience Non-Hallucination73.713.4

scicode51.218.3

TauBench V3 - Banking34.66.8

Terminal-Bench 2.182.725.8

Terminal-Bench Hard50.818.2

τ²-Bench Telecom (AA run)99.192.1

τ³-Bench26.88.2

τ³-Bench Banking26.85.5

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. Quoted rates are the price-setter row we currently track for each model — its direct or vendor-official listing where one exists (zai-official, direct), otherwise the lowest tracked offer.

Compare GLM-5.2 withALL PAIRINGS →

Z.aiGLM-5.1

Across the fieldGemini 3.6 Flash Nemotron 3 Super 120B A12B GPT-5.5 Claude Opus 4.8 GPT-4o GPT-5.6 Sol Gemini 3.1 Pro GPT-5.4

Compare Qwen3.5 4B 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