Qwen 3 8B is a 8B model. Supports switching between thinking and non thinking: trigger thinking with /think and /no_think anywhere in a prompt or system message to toggle chain-of-thought reasoning.
Context Window
41.0K
Max Output
32.8K
Input Price (Auto)
$0.47/1M
Output Price (Auto)
$0.47/1M
Cache Read (Auto)
$0.23/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
5.1
Reasoning
GPQA Diamond
Graduate-level scientific reasoning
45.2%
Better than 23% of models compared
HLE
Humanity's Last Exam
2.8%
Better than 1% of models compared
IFBench
Instruction-following benchmark
28.6%
Better than 13% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
24.9%
Better than 29% of models compared
AA-LCR
Long context reasoning evaluation
0.0%
Better than 7% of models compared
CritPt
Research-level physics reasoning
0.0%
Coding
SciCode
Python programming for scientific computing
16.8%
Better than 18% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
2.3%
Better than 20% of models compared
LiveCodeBench
Contamination-free coding benchmark
20.2%
Better than 22% of models compared
Math
AIME 2025
American Invitational Mathematics Examination 2025
24.3%
Better than 26% of models compared
AIME
American Invitational Mathematics Examination
24.3%
Better than 51% of models compared
Math-500
Diverse mathematical problem solving benchmark
82.8%
Better than 49% of models compared
Knowledge
MMLU-Pro
Professional and academic subject knowledge
64.3%
Better than 26% of models compared
AA-Omniscience Accuracy
Proportion of correctly answered questions
11.1%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
95.6%
Last updated Jun 28, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare Qwen 3 8B with similar models from the same provider or model family.
Qwen3.6 35B A3B Thinking
Qwen/Qwen3.6-35B-A3B:thinkingQwen3.6 35B A3B is a native vision-language MoE model with hybrid attention. Compared to Qwen3.5 35B A3B, Alibaba reports stronger agentic coding, mathematical and code reasoning, and better spatial understanding (including object localization and detection).
Qwen3.6 35B A3B
Qwen/Qwen3.6-35B-A3BQwen3.6 35B A3B is a native vision-language MoE model with hybrid attention. Compared to Qwen3.5 35B A3B, Alibaba reports stronger agentic coding, mathematical and code reasoning, and better spatial understanding (including object localization and detection).
Qwen 3 Coder 480B
qwen/qwen3-coderQwen 3 Coder 480B, a 480 billion total parameter model with 35B active, and 160 total experts with 8 active. Performs similar to Claude 4 Sonnet in coding benchmarks, but does so at a much lower price.
Qwen3.5 9B
qwen/qwen3.5-9bQwen3.5 9B is a multimodal foundation model from the Qwen 3.5 family, built for efficient reasoning, coding, and visual understanding in a compact 9B architecture.
Qwen3.5 397B A17B
qwen/qwen3.5-397b-a17bQwen 3.5's open-source 397B MoE model (17B active params) with hybrid linear attention. Supports text, image, and video input with a 256K context window.
Qwen3.5 397B A17B Thinking
qwen/qwen3.5-397b-a17b-thinkingQwen 3.5's open-source 397B MoE model (17B active params) with hybrid linear attention and extended reasoning. Supports text, image, and video input with a 256K context window.