Qwen3 4B (Reasoning)

Qwen3 4B (Reasoning)

Alibaba · Released Apr 28, 2025 Professional
Intelligence #14 / 590
82.0 Our Score
Speed #125 / 279
103.9 tokens / sec
Input #224 / 592
$0.110 per 1M tokens
Output #354 / 592
$1.26 per 1M tokens
Context
— Not reported

Analysis Summary

Qwen3 4B Reasoning is Alibaba's April 2025 compact reasoning model, priced at $0.11 input and $1.26 output per million tokens. With an intelligence index of 8.4, LiveCodeBench at 0.465, and MMLU-Pro at 0.696, it delivers strong coding and reasoning performance for its size and price point.

For businesses, it is well suited to cost-sensitive coding assistance, automated code review, and structured content tasks where budget is a primary constraint. The agentic index of 19 and tau2 of 0.190 suggest reasonable multi-step task capability. Instruction following (IFBench 0.325) is moderate, and long-context data is absent, limiting its fit for document-heavy workflows.

A -4 point regional penalty applies. At $0.11 per million input tokens, it offers strong value for coding-focused automation. Teams needing the best compact coding model at minimal cost should also evaluate the newer 2507 variant, which posts higher benchmark scores.

Assessed June 30, 2026

Editorial notes

Qwen3 4B Reasoning from Alibaba offers strong coding performance at LiveCodeBench 0.465 and competitive MMLU-Pro at 0.696, priced at $0.11 input, making it a cost-effective compact coding model.

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence2.1Technical2.8Value7Content3.6
Intelligence 2.1/10
Technical 2.8/10
Content 3.6/10
Value 7/10

How Qwen3 4B (Reasoning) compares

Qwen3 4B (Reasoning) ranks #262 of 385 AI models we track for overall intelligence, #188 of 293 for agentic tasks. At $0.11 per million input tokens it is cheaper than 62% of comparable models.

Performance Indices

Source: Artificial Analysis

8.4 Intelligence Index
19 Agentic Index
22.3 Math Index

Benchmark Scores

Intelligence

GPQA Diamond 52.2% Graduate-level scientific reasoning
HLE 5.1% Humanity's Last Exam
MMLU Pro 69.6% Multi-task language understanding
MATH 500 93.3% Mathematical problem-solving
AIME 65.7% Competition mathematics
AIME 2025 22.3% Competition mathematics (2025)
SciCode 3.5% Scientific computing

Technical

LiveCodeBench 46.5% Live coding evaluation
τ²-Bench 19% Conversational agent benchmark

Content

IFBench 32.5% Instruction following

Benchmark data from Artificial Analysis and Hugging Face

How does Qwen3 4B (Reasoning) stack up?

Compare side-by-side with other professional models.

Compare Models

Model Information

ProviderAlibaba
Release Date April 28, 2025
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $0.11 $0.000110
Output $1.26 $0.001260

Leaderboard Categories

Frequently asked questions about Qwen3 4B (Reasoning)

How much does Qwen3 4B (Reasoning) cost?

Qwen3 4B (Reasoning) costs $0.11 per million input tokens and $1.26 per million output tokens.

Who created Qwen3 4B (Reasoning)?

Qwen3 4B (Reasoning) is developed by Alibaba and was released on April 28, 2025.