Bluesky Thread

Qwen3-4B Instruct & Thinking

View original thread
Qwen3-4B Instruct & Thinking

uuuh, guys this isn’t a boring model

This crushes all the agentic benchmarks, even beating out the already-impressive qwen3-30b-a4b

It’s hanging with some already impressive mid-sized models at only 4B
Bar chart comparing performance of four Qwen3-4B model variants—Thinking-2507 (red), Thinking (gray), Instruct-2507 (blue), and Non-Thinking (beige)—across five benchmarks: 1. GPQA • Thinking-2507: 65.8 • Thinking: 62.0 • Instruct-2507: 55.9 • Non-Thinking: 41.7 2. AIME25 • Thinking-2507: 81.3 • Thinking: 65.6 • Instruct-2507: 47.4 • Non-Thinking: 19.1 3. LiveCodeBench v6 (25.02–25.05) • Thinking-2507: 55.2 • Thinking: 48.4 • Instruct-2507: 35.1 • Non-Thinking: 26.4 4. Arena-Hard v2 • Thinking-2507: 34.9 • Instruct-2507: 43.4 • Thinking: 13.7 • Non-Thinking: 9.5 5. BFCL-v3 • Thinking-2507: 71.2 • Thinking: 65.9 • Instruct-2507: 61.9 • Non-Thinking: 57.6 Across all benchmarks, the Thinking-2507 variant (red bars) consistently leads in performance except for Arena-Hard v2, where Instruct-2507 scores highest. A watermark-style logo is faintly visible in the background behind the bars.
55 4
huggingface.co/Qwen/Qwen3-4...
huggingface.co
Qwen/Qwen3-4B-Thinking-2507 · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
4 1
55 likes 4 reposts

More like this

it’s here! a real Qwen3 model

Qwen3-Next-80B-A3B Base, Instruct & Thinking

i can’t get over this — qwen3 32B dense is only *slightly* better than 30B-A3B
×