Better than 61% of all models
Context
N/A
Input $/1M
TBD
Output $/1M
TBD
Type
text-generation
License
Open Source
Benchmarks
12 tested
Data updated today
About
Qwen text generation model. 2605K downloads on HuggingFace.
Tested on 12 benchmarks with 44.4% average. Top scores: GSM8K (86.7%), HellaSwag (69.1%), IFEval (61.0%).
Capabilities
coding
57.9
#62 globally
reasoning
9.5
#166 globally
math
61.9
#57 globally
knowledge
42.0
#169 globally
language
61.0
#99 globally
general
28.9
#33 globally
Benchmark Scores
Compare AllTested on 12 benchmarks · Ranked across 6 categories
Score Distribution (all 274 models)
0255075100
▲ You are here
codingCompare coding →
Aider — Code Editing
57.9—Code editing benchmark from the Aider project. Measures ability to apply targeted code changes while maintaining correctness and style.
reasoningCompare reasoning →
MUSR
9.5—HuggingFace MuSR (Multi-Step Reasoning). Tests multi-hop reasoning requiring chaining multiple facts together.
mathCompare math →
GSM8K
86.7—Grade school math word problems. 8,500 problems testing multi-step arithmetic reasoning. A foundational math benchmark.
MATH Level 5
37.2—HuggingFace evaluation of MATH Level 5 problems. Competition math requiring advanced reasoning and proof construction.
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Research
Documentation
Community
Source Code
BenchGecko API
qwen-qwen25-coder-7b-instruct
Specifications
- Typetext-generation
- ContextN/A
- ReleasedSep 2024
- LicenseOpen Source
- StatusActive
Available On
Learn More
Share & Export
Frequently Asked Questions
Qwen2.5 Coder 7B Instruct is an open-source text-generation AI model by Alibaba, released in September 2024. It has an average benchmark score of 56.6.