Skip to main content
Back to Explore

Qwen3 VL 4B (Reasoning)

Alibaba·Released 2025-10-14
Open Source
Compare

Related Models

Qwen: Qwen3.7 Plus2026-06-03Qwen: Qwen3.7 Max2026-05-21Qwen: Qwen3.6 27B2026-04-27Qwen: Qwen3.6 35B A3B2026-04-27Qwen: Qwen3.5 Plus 2026-04-202026-04-27Qwen: Qwen3.6 Flash2026-04-27Qwen: Qwen3.6 Max Preview2026-04-27Qwen3.6 27B (Non-reasoning)2026-04-22

Benchmarks

MMLU-Pro
70.0%
GPQA Diamond
49.4%
HLE
4.4%
LiveCodeBench
32.0%
SciCode
17.1%
TerminalBench Hard
1.5%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
25.7%
IFBench
36.6%
Long Context Recall
21.3%
Tau2
15.5%
Market AverageTop Score

Open Source

Quick Compare

Similar Models

OpenAI: GPT-4 Turbo

OpenAI

Q: 7.9$15.00/1M128K ctx
Coding: +14.8

GPT-5 nano (minimal)

OpenAI

Q: 8.0$0.14/1M
Coding: +7.5

Gemini 1.5 Flash (Sep '24)

Google

Q: 8.0N/A/1M

Grok 2 (Dec '24)

xAI

Q: 8.0N/A/1M

Solar Pro 2 (Non-reasoning)

Upstage

Q: 7.8N/A/1M
Coding: +4.6

Olmo 3.1 32B Think

Allen AI

Q: 8.1$0.24/1M66K ctx
Coding: +3.1
Compare all 7 models