Qwen: Qwen3 8B

Qwen: Qwen3 8B

qwen · Released Apr 28, 2025 Efficient
Intelligence #243 / 571
36.4 Our Score
Speed #175 / 266
64.7 tokens / sec
Input #155 / 571
$0.050 per 1M tokens
Output #223 / 571
$0.400 per 1M tokens
Context #231 / 571
131,072 tokens

Analysis Summary

Qwen: Qwen3 8B comes from Qwen. It was released in April 2025. We place it in the Efficient tier, where it sits at #243 of 571 models overall. For raw reasoning ability it ranks #297 of 374, putting it in the broader field for overall intelligence.

On coding it ranks #259 of 311, a reasonable fit for everyday development support. It also ranks #227 of 286 for agentic, multi-step tasks — the autonomous, tool-driven workflows that underpin business automation. Its 131K-token context window is larger than 60% of the models we list, suiting long documents, large codebases, and retrieval-heavy workloads. Crucially for business adoption, Qwen: Qwen3 8B combines tool use, function calling, and step-by-step reasoning in a single model, letting teams consolidate several use cases instead of stitching together multiple services.

At $0.050 input and $0.400 output per 1M tokens, Qwen: Qwen3 8B is aggressively priced for high-volume use which makes it easy to justify for cost-sensitive, high-throughput deployments. Qwen: Qwen3 8B suits cost-sensitive or high-volume deployments where efficiency matters more than topping the benchmarks.

Editorial notes

Qwen3 8B is a compact open-weight model with tool use and function calling, a 128K context, and very low pricing; reasoning depth is limited but cost-efficiency is strong for simple tasks.

Assessed May 31, 2026

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

Performance Profile

Intelligence2.2Technical1.6Value7.8Content3.5
Intelligence 2.2/10
Technical 1.6/10
Content 3.5/10
Value 7.8/10

How Qwen: Qwen3 8B compares

Qwen: Qwen3 8B ranks #297 of 374 AI models we track for overall intelligence, #259 of 311 for coding, #227 of 286 for agentic tasks. Its 131K-token context window is larger than 60% of the models we list. At $0.05 per million input tokens it is cheaper than 73% of comparable models.

About Qwen: Qwen3 8B

Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between "thinking" mode for math,..

8B Parameters

Capabilities

Tool Use Function Calling

Architecture Detail

Instruct Typeqwen3

Performance Indices

Source: Artificial Analysis

10.6 Intelligence Index
7.1 Coding Index
13.6 Agentic Index
24.3 Math Index

Benchmark Scores

Intelligence

GPQA Diamond 45.2% Graduate-level scientific reasoning
HLE 2.8% Humanity's Last Exam
MMLU Pro 64.3% Multi-task language understanding
MATH 500 82.8% Mathematical problem-solving
AIME 24.3% Competition mathematics
AIME 2025 24.3% Competition mathematics (2025)
SciCode 16.8% Scientific computing

Technical

LiveCodeBench 20.2% Live coding evaluation
TerminalBench Hard 2.3% Agentic terminal tasks
τ²-Bench 24.9% Conversational agent benchmark

Content

IFBench 28.6% Instruction following

Benchmark data from Artificial Analysis and Hugging Face

How does Qwen: Qwen3 8B stack up?

Compare side-by-side with other efficient models.

Compare Models

Model Information

OpenRouter ID qwen/qwen3-8b
Providerqwen
Release Date April 28, 2025
Context Length131,072 tokens
Max Completion8,192 tokens
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $0.05 $0.000050
Output $0.40 $0.000400

Live Performance

Live endpoint metrics, refreshed every 30 minutes.

99.9%
Avg Uptime
788ms
Best Latency (TTFT)
55 tok/s
Best Throughput
2/2
Active Endpoints
Available via: AtlasCloud, Alibaba

Leaderboard Categories

Frequently asked questions about Qwen: Qwen3 8B

How much does Qwen: Qwen3 8B cost?

Qwen: Qwen3 8B costs $0.05 per million input tokens and $0.40 per million output tokens.

What is the context window of Qwen: Qwen3 8B?

Qwen: Qwen3 8B has a context window of 131,072 tokens (131K).

Is Qwen: Qwen3 8B good for coding?

On our coding benchmark index, Qwen: Qwen3 8B ranks #259 of 311 models, placing it in the broader range of the field for code generation and debugging.

What can Qwen: Qwen3 8B do?

Qwen: Qwen3 8B supports tool use and function calling.

Who created Qwen: Qwen3 8B?

Qwen: Qwen3 8B is developed by Qwen and was released on April 28, 2025.