Which is better, Gemini 2.5 Pro or Qwen3.5 2B?

Gemini 2.5 Pro vs Qwen3.5 2B

29 SHARED BENCHMARKS

Across 29 shared benchmarks, Gemini 2.5 Pro scores higher on 26 and Qwen3.5 2B on 3. The widest gap is Terminal-Bench 2.1, where Gemini 2.5 Pro scores 28.5 against 3.

GOOGLEVSALIBABA29 SHARED26–3 HEAD-TO-HEAD

BenchmarkGemini 2.5 ProMARGINQwen3.5 2B

AA Agentic Index7.10.8

AA Intelligence266.9

AA-LCR6925.6

AA-Omniscience-14.3-60.2

AIME 20249217

AIME 202588.319

Artificial Analysis Coding Index46.72.9

critpt2.60

gdpval80

Global-MMLU-Lite89.264.5

GPQA Diamond86.451.6

HLE21.65

IFBench4941.3

longbench_v26538.7

math_500_em98.881.5

MathVista83.948.7

MMLU-Pro8666.5

MMMU-Pro74.943

MMStar79.255.1

multichallenge53.633.7

OCRBench85.986.1

OmniScience Accuracy398.1

OmniScience Non-Hallucination12.625.8

scicode46.37.2

TauBench V3 - Banking9.72.5

Terminal-Bench 2.128.53

Terminal-Bench Hard26.53.8

τ²-Bench Telecom (AA run)54.181.6

τ³-Bench9.36.2

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 Gemini 2.5 Pro withALL PAIRINGS →

GoogleGemini 3.1 Pro Gemini 3 Pro Gemma 4 26B A4B Gemini 1.5 Pro Gemma 4 31B Gemma 4 E2B

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 fieldGemini 1.5 Pro Claude Sonnet 4 Claude Sonnet 5 Muse Spark 1.1 GLM-5.1 GLM-5.2 o4-mini Claude Sonnet 4.6