Qwen3 1.7B (Reasoning)
Analysis Summary
Qwen3 1.7B (Reasoning) is Alibaba's 1.7-billion-parameter thinking-mode model, released in April 2025. Its math index of 38.7 and livecodebench score of 0.308 are strong for its size, and an agentic index of 26 suggests some multi-step capability. MMLU Pro of 0.570 is reasonable for a model of this scale.
For businesses, it is best suited to lightweight reasoning tasks, simple structured content, and edge deployments where model size is constrained. Instruction-following (ifbench: 0.269) is modest, and coding capability is minimal, so it should not be used for software engineering or complex content workflows.
At $0.11 input and $1.26 output per million tokens, it offers good value for its capability tier. Teams needing a small, cheap reasoning model for simple analytical or classification tasks will find it useful, but those with more demanding requirements should step up to the 4B or larger variants.
Assessed June 6, 2026
Editorial notes
Qwen3 1.7B (Reasoning) from Alibaba shows strong math and agentic scores for a sub-2B model, with reasonable livecodebench performance, but overall capability is limited for professional business workflows.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Qwen3 1.7B (Reasoning) compares
Qwen3 1.7B (Reasoning) ranks #350 of 378 AI models we track for overall intelligence, #300 of 315 for coding, #152 of 289 for agentic tasks. At $0.11 per million input tokens it is cheaper than 61% of comparable models.
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Qwen3 1.7B (Reasoning) stack up?
Compare side-by-side with other professional models.
Model Information
| Provider | Alibaba |
| 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 |
Frequently asked questions about Qwen3 1.7B (Reasoning)
How much does Qwen3 1.7B (Reasoning) cost?
Qwen3 1.7B (Reasoning) costs $0.11 per million input tokens and $1.26 per million output tokens.
Is Qwen3 1.7B (Reasoning) good for coding?
On our coding benchmark index, Qwen3 1.7B (Reasoning) ranks #300 of 315 models, placing it in the broader range of the field for code generation and debugging.
Who created Qwen3 1.7B (Reasoning)?
Qwen3 1.7B (Reasoning) is developed by Alibaba and was released on April 28, 2025.
