Which is better, Gemini 3.1 Pro or Qwen3.5 4B?

Gemini 3.1 Pro vs Qwen3.5 4B

27 SHARED BENCHMARKS

Across 27 shared benchmarks, Gemini 3.1 Pro scores higher on 25 and Qwen3.5 4B on 2. The widest gap is τ³-Bench, where Gemini 3.1 Pro scores 67.1 against 8.2. Qwen3.5 4B is the cheaper of the two on tracked API pricing ($0.03 against $2.00 per million input tokens).

GOOGLEVSALIBABA27 SHARED25–2 HEAD-TO-HEAD

BenchmarkGemini 3.1 ProMARGINQwen3.5 4B

AA Agentic Index21.436.3

AA Intelligence46.520

AA-LCR8263

AA-Omniscience32.9-58.4

aime_202698.399

Artificial Analysis Coding Index68.822.6

critpt17.70

gdpval23.18.3

GPQA Diamond94.377.1

HLE51.49.9

hmmt_feb_202694.784.1

IFBench77.159.2

LiveCodeBench v691.755.8

MMLU-Pro9179.1

mmmlu92.676.1

MMMU-Pro8365.4

multichallenge71.449

OmniScience Accuracy55.315.1

OmniScience Non-Hallucination50.113.4

scicode5918.3

t2-bench99.379.9

TauBench V3 - Banking21.46.8

Terminal-Bench 2.17425.8

Terminal-Bench Hard68.518.2

τ²-Bench Telecom (AA run)99.392.1

τ³-Bench67.18.2

τ³-Bench Banking16.55.5

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 (direct, direct), otherwise the lowest tracked offer.

Compare Gemini 3.1 Pro withALL PAIRINGS →

GoogleGemini 3 Pro Gemma 4 26B A4B Gemini 2.5 Pro Gemini 1.5 Pro Gemma 4 31B Gemma 4 E2B

Across the fieldGemini 3.6 Flash Nemotron 3 Super 120B A12B GPT-5.5 Claude Opus 4.8 GPT-4o GPT-5.6 Sol GPT-5.4 GPT-5.2

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 fieldGPT-5.4 GPT-5.2 Claude Opus 4.6 Claude Sonnet 4.5 Claude 3.5 Sonnet Gemini 3 Pro Claude Fable 5 GPT-5