Better than 82% of all models
Context
N/A
Input $/1M
TBD
Output $/1M
TBD
Type
text
License
Open Source
Benchmarks
8 tested
Data updated today
About
Tested on 8 benchmarks with 61.0% average. Top scores: OpenBookQA (84.0%), ARC AI2 (79.9%), HellaSwag (68.9%).
Capabilities
reasoning
62.3
#31 globally
knowledge
60.9
#44 globally
Benchmark Scores
Compare AllTested on 8 benchmarks · Ranked across 2 categories
Score Distribution (all 233 models)
0255075100
▲ You are here
reasoningCompare reasoning →
BBH
62.3—BIG-Bench Hard. 23 challenging tasks from BIG-Bench where prior language models fell below average human performance.
knowledgeCompare knowledge →
OpenBookQA
84.0—Elementary science questions with access to a small book of core science facts. Tests reasoning beyond memorization.
ARC AI2
79.9—AI2 Reasoning Challenge. Grade-school science questions requiring multi-step reasoning. Easy and Challenge sets test different difficulty levels.
HellaSwag
68.9—Sentence completion requiring commonsense reasoning about physical and social situations. Tests real-world understanding.
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Research
Documentation
Community
Source Code
BenchGecko API
phi-3-mini-3-8b
Specifications
- Typetext
- ContextN/A
- ReleasedJan 2024
- LicenseOpen Source
- Statusbenchmark-only
Available On
Learn More
Share & Export
Frequently Asked Questions
phi-3-mini 3.8B is an open-source text AI model by Microsoft, released in January 2024. It has an average benchmark score of 68.3.