Refresh Models —Deals —Regulatory —Sources —

o1 vs Qwen3.5 2B

20 SHARED BENCHMARKS

Across 20 shared benchmarks, o1 scores higher on 19 and Qwen3.5 2B on 1. The widest gap is scicode, where o1 scores 35.8 against 7.2.

OPENAIVSALIBABA20 SHARED19–1 HEAD-TO-HEAD

Benchmarko1MARGINQwen3.5 2B

AA Agentic Index31.10.8

AA Intelligence23.46.9

AA-LCR6525.6

AA-Omniscience-10.6-60.2

AIME 202479.217

AIME 202581.719

Artificial Analysis Coding Index39.72.9

GPQA Diamond75.751.6

HLE7.75

IFBench70.341.3

math_500_em96.481.5

MathVista71.848.7

mmmlu87.763.1

OmniScience Accuracy34.78.1

OmniScience Non-Hallucination30.725.8

scicode35.87.2

Terminal-Bench Hard12.93.8

τ²-Bench Telecom (AA run)62.681.6

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 o1 withALL PAIRINGS →

OpenAIGPT-5.5 GPT-4o GPT-5.6 Sol GPT-5.4 GPT-5.2 GPT-5

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 fieldGemma 4 31B Kimi K2 Instruct Gemma 4 E2B GPT-4o mini Qwen3.6 35B A3B Gemini 3.5 Flash GPT-6 Astra MiniMax M2.7