Qwen: Qwen3 Max Thinking
Analysis Summary
Qwen3 Max Thinking is a reasoning-focused model from Alibaba's Qwen family, with a strong mathematics index of 82.3 and a GPQA score of 0.776. Its intelligence index of 32.5 places it in the good tier, and the long-context reasoning score (lcr 0.577) is above average. Tool use and function calling are supported across a 262K context window.
For businesses, the model's strengths are in analytical and scientific tasks, structured content generation, and workflows requiring deep reasoning over complex inputs. However, its coding index of 24.5 and agentic index of 50.5 are below what the field's top models offer, limiting its utility for software engineering agents or complex multi-step automation. Pricing at $0.78 input and $3.90 output is relatively high for this capability tier.
Qwen3 Max Thinking suits teams with specific analytical or mathematical workloads rather than general-purpose business automation. A -4 point regional penalty applies given the provider's limited enterprise presence outside its home market.
Assessed June 6, 2026
Editorial notes
Qwen3 Max Thinking excels at mathematics and scientific reasoning with an AIME score of 0.823, but its coding and agentic indices are below the level expected for a model at this price point.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Qwen: Qwen3 Max Thinking compares
Qwen: Qwen3 Max Thinking ranks #94 of 378 AI models we track for overall intelligence, #118 of 315 for coding, #81 of 289 for agentic tasks. Its 262K-token context window is larger than 81% of the models we list. At $0.78 per million input tokens it is cheaper than 28% of comparable models.
About Qwen: Qwen3 Max Thinking
Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Qwen: Qwen3 Max Thinking stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
qwen/qwen3-max-thinking
|
| Provider | qwen |
| Release Date | February 9, 2026 |
| Context Length | 262,144 tokens |
| Max Completion | 32,768 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.78 | $0.000780 |
| Output | $3.90 | $0.003900 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about Qwen: Qwen3 Max Thinking
How much does Qwen: Qwen3 Max Thinking cost?
Qwen: Qwen3 Max Thinking costs $0.78 per million input tokens and $3.90 per million output tokens.
What is the context window of Qwen: Qwen3 Max Thinking?
Qwen: Qwen3 Max Thinking has a context window of 262,144 tokens (262K).
Is Qwen: Qwen3 Max Thinking good for coding?
On our coding benchmark index, Qwen: Qwen3 Max Thinking ranks #118 of 315 models, placing it in the broader range of the field for code generation and debugging.
What can Qwen: Qwen3 Max Thinking do?
Qwen: Qwen3 Max Thinking supports tool use and function calling.
Who created Qwen: Qwen3 Max Thinking?
Qwen: Qwen3 Max Thinking is developed by Qwen and was released on February 9, 2026.
