Which is better, GPT-5 or Qwen3.5 2B?

GPT-5 vs Qwen3.5 2B

23 SHARED BENCHMARKS

Across 23 shared benchmarks, GPT-5 scores higher on 22 and Qwen3.5 2B on 1. The widest gap is Terminal-Bench Hard, where GPT-5 scores 37.9 against 3.8.

OPENAIVSALIBABA23 SHARED22–1 HEAD-TO-HEAD

BenchmarkGPT-5MARGINQwen3.5 2B

AA Agentic Index49.70.8

AA Intelligence356.9

AA-LCR78.225.6

AA-Omniscience-8.7-60.2

AIME 20259519

Artificial Analysis Coding Index38.92.9

critpt5.70

gdpval32.50

GPQA Diamond87.351.6

HLE28.55

IFBench73.141.3

mmlu_redux95.379.6

MMLU-Pro87.566.5

MMMU-Pro78.443

multichallenge71.133.7

OmniScience Accuracy40.38.1

OmniScience Non-Hallucination2125.8

scicode437.2

TauBench V3 - Banking22.12.5

Terminal-Bench 2.135.23

Terminal-Bench Hard37.93.8

τ²-Bench Telecom (AA run)86.581.6

τ³-Bench19.66.2

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 GPT-5 withALL PAIRINGS →

OpenAIGPT-5.5 GPT-4o GPT-5.6 Sol GPT-5.4 GPT-5.2 o3

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 fieldClaude Opus 4.5 DeepSeek-V4-Pro DeepSeek-V3 Kimi K2.6 Kimi K2.5 o3 GPT-5.1 Claude Opus 5