58.4
avg score
Rank #95
Better than 65% of all models
Context
N/A
Input $/1M
TBD
Output $/1M
TBD
Type
text
License
Open Source
Benchmarks
13 tested
Data updated today
About
Tested on 13 benchmarks with 39.0% average. Top scores: CMMLU (89.7%), MMLU (76.5%), Aider — Code Editing (55.6%).
Capabilities
coding
33.5
#133 globally
reasoning
19.7
#125 globally
math
35.1
#143 globally
knowledge
51.8
#108 globally
agentic
1.1
#52 globally
language
38.2
#134 globally
general
51.9
#9 globally
Benchmark Scores
Compare AllTested on 13 benchmarks · Ranked across 7 categories
Score Distribution (all 274 models)
0255075100
▲ You are here
codingCompare coding →
Aider — Code Editing
55.6—Code editing benchmark from the Aider project. Measures ability to apply targeted code changes while maintaining correctness and style.
WeirdML
11.3—Unusual and adversarial machine learning challenges. Tests robustness of reasoning about edge cases in ML systems.
reasoningCompare reasoning →
MUSR
19.7—HuggingFace MuSR (Multi-Step Reasoning). Tests multi-hop reasoning requiring chaining multiple facts together.
mathCompare math →
MATH level 5
39.1—Competition-level math from AMC, AIME, and olympiad problems. Level 5 is the hardest tier, requiring creative problem-solving.
MATH Level 5
31.1—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
qwen2-72b
Specifications
- Typetext
- ContextN/A
- ReleasedJan 2024
- LicenseOpen Source
- Statusbenchmark-only
Available On
Learn More
Share & Export
Frequently Asked Questions
Qwen2-72B is an open-source text AI model by Alibaba Qwen, released in January 2024. It has an average benchmark score of 58.4.