Qwen text generation model. 2605K downloads on HuggingFace.
Tested on 12 benchmarks · BenchGecko score 56.3. Top scores: GSM8K (86.7%), HellaSwag (69.1%), IFEval (61.0%).
Code editing benchmark from the Aider project. Measures ability to apply targeted code changes while maintaining correctness and style.
HuggingFace MuSR (Multi-Step Reasoning). Tests multi-hop reasoning requiring chaining multiple facts together.
Grade school math word problems. 8,500 problems testing multi-step arithmetic reasoning. A foundational math benchmark.
HuggingFace evaluation of MATH Level 5 problems. Competition math requiring advanced reasoning and proof construction.
- Typetext-generation
- ContextN/A
- ReleasedSep 2024
- LicenseOpen Source
- StatusActive
Frequently Asked Questions
Key facts · as of 2026-06-22
- Qwen2.5 Coder 7B Instruct by Alibaba. BenchGecko score 56.3, rank 109 of 312 scored models (normalized average of public benchmark scores).
- List price n/a input · n/a output per 1M tokens (as of 2026-06-22).
How to cite · data as of 2026-06-22
Qwen2.5 Coder 7B Instruct · benchmarks, pricing and providers. BenchGecko, data as of 2026-06-22. https://benchgecko.ai/model/qwen-qwen25-coder-7b-instruct
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP