Alibaba Cloud / Qwen Team model product
Qwen2.5-Coder is a specialized coding model trained on 5.5 trillion tokens of code data, supporting 92 programming languages with a 128K context window. It excels in code generation, completion, and repair while maintaining strong performance in math and general tasks. The model demonstrates exceptional capabilities in multi-programming language tasks and code reasoning.
Updated Aug 10, 2026. Default version: Qwen2.5-Coder 7B Instruct
Structured fields from the published default version.
This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.
Published benchmark records for the scored version Qwen2.5-Coder 7B Instruct.
| CRUXEval-Input-CoT | 0.6 | 1 | 1 | 100.0% | C | |
| CRUXEval-Output-CoT | 0.6 | 1 | 1 | 100.0% | C | |
| MMLU-Base | 0.7 | 1 | 1 | 100.0% | C | |
| STEM | 0.3 | 1 | 1 | 100.0% | C | |
| BigCodeBench | 0.4 | 2 | 2 | 0.0% | C | |
| Aider | 0.6 | 3 | 4 | 33.3% | C | |
| TheoremQA | 0.3 | 5 | 6 | 20.0% | C | |
| MBPP | 0.8 | 9 | 37 | 77.8% | C | |
| Winogrande | 0.7 | 15 | 22 | 33.3% | C | |
| TruthfulQA | 0.5 | 17 | 18 | 5.9% | C | |
| HellaSwag | 0.8 | 21 | 27 | 23.1% | C | |
| HumanEval | 0.9 | 26 | 76 | 66.7% | C | |
| ARC-C | 0.6 | 30 | 34 | 12.1% | C | |
| GSM8k | 0.8 | 36 | 48 | 25.5% | C | |
| MMLU-Redux | 0.7 | 46 | 48 | 4.3% | C | |
| MATH | 0.5 | 61 | 71 | 14.3% | C | |
| LiveCodeBench | 0.2 | 66 | 73 | 9.7% | C | |
| MMLU | 0.7 | 89 | 100 | 11.1% | C | |
| MMLU-Pro | 0.4 | 127 | 129 | 1.6% | C |
Preference and agent-evaluation signals from published Arena datasets.
The default version has no published Arena rows, or its source alias has not been resolved.
Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.
| Alibaba (China) | qwen2-5-coder-7b-instruct | global | $0.144 | $0.287 | 131.1K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.
| Qwen2.5-Coder 7B Instruct | 24.4 | 7B | N/A | N/A | No | Apache 2.0 |
A concise description based on the published model registry.
Qwen2.5-Coder is a specialized coding model trained on 5.5 trillion tokens of code data, supporting 92 programming languages with a 128K context window. It excels in code generation, completion, and repair while maintaining strong performance in math and general tasks. The model demonstrates exceptional capabilities in multi-programming language tasks and code reasoning.
Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.
Data snapshot: 2026-08-07. Editorial model content is not available in the backend.
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest published LLMBoard score.
Common questions about Qwen2.5 Coder 7B.
Qwen2.5 Coder 7B's default version was released on Sep 19, 2024.
Qwen2.5 Coder 7B's official API price is $0.144 per million input tokens and $0.287 per million output tokens via Alibaba (China).
Qwen2.5 Coder 7B is published under Alibaba Cloud / Qwen Team in the model registry.
The current registry does not publish a context window for the default version.
No. The default version is not marked as having publicly available weights.
1 published provider offerings are linked to the default version.
Nearby ranked alternatives include Gemma 4 E4B, Phi 3.5 mini, Qwen3 VL 30B A3B.