Qwen: Qwen3 Next 80B A3B Thinking
Analysis Summary
Qwen3 Next 80B A3B Thinking is a mixture-of-experts model from Qwen with a 262K context window, tool use, and function calling. Its instruction-following benchmark (ifbench 0.607) and long-context reasoning score are among the stronger results in this batch, and its math index is high at 84.3.
For businesses, the model suits structured content generation, document analysis, and instruction-heavy workflows where precision and consistency matter. Its agentic index of 25.7 and coding index of 19.5 are modest, limiting its value for autonomous agent pipelines or serious software development tasks.
Pricing is attractive at $0.0975 input and $0.78 output per million tokens, making it cost-effective for content-focused deployments. Teams needing reliable instruction following and strong math reasoning at a low cost will find it a practical choice, provided they do not require deep coding or agentic capability.
Assessed June 17, 2026
Editorial notes
Qwen3 Next 80B A3B Thinking delivers strong instruction-following and math reasoning with a 262K context window and competitive pricing, though its agentic and coding scores are moderate.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Qwen: Qwen3 Next 80B A3B Thinking compares
Qwen: Qwen3 Next 80B A3B Thinking ranks #138 of 380 AI models we track for overall intelligence, #149 of 317 for coding, #157 of 292 for agentic tasks. Its 262K-token context window is larger than 81% of the models we list. At $0.10 per million input tokens it is cheaper than 66% of comparable models.
About Qwen: Qwen3 Next 80B A3B Thinking
Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured āthinkingā traces by default. Itās designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Qwen: Qwen3 Next 80B A3B Thinking stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
qwen/qwen3-next-80b-a3b-thinking
|
| Provider | qwen |
| Release Date | September 11, 2025 |
| Context Length | 262,144 tokens |
| Max Completion | 32,768 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.10 | $0.000098 |
| Output | $0.78 | $0.000780 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about Qwen: Qwen3 Next 80B A3B Thinking
How much does Qwen: Qwen3 Next 80B A3B Thinking cost?
Qwen: Qwen3 Next 80B A3B Thinking costs $0.10 per million input tokens and $0.78 per million output tokens.
What is the context window of Qwen: Qwen3 Next 80B A3B Thinking?
Qwen: Qwen3 Next 80B A3B Thinking has a context window of 262,144 tokens (262K).
Is Qwen: Qwen3 Next 80B A3B Thinking good for coding?
On our coding benchmark index, Qwen: Qwen3 Next 80B A3B Thinking ranks #149 of 317 models, placing it in the broader range of the field for code generation and debugging.
What can Qwen: Qwen3 Next 80B A3B Thinking do?
Qwen: Qwen3 Next 80B A3B Thinking supports tool use and function calling.
Who created Qwen: Qwen3 Next 80B A3B Thinking?
Qwen: Qwen3 Next 80B A3B Thinking is developed by Qwen and was released on September 11, 2025.
