This website uses cookies for authentication, support chat, and analytics. Only authentication cookies are turned on by default.
Don’t Enable
Enable All
Statistics
Templates
Feed
Public Projects
Log In
Animate this data
Bar chart race of Phi-3-small-8k-instruct, gemini-4-argon_high, gpt-6-astra_max and 7 more, by GPQA Diamond.
Create it free
Takes a free account
Phi-3-small-8k-instruct
Adversarial Nli
58 %
Bbh
79 %
Hella Swag
77 %
Live bench
24 %
Mmlu
76 %
Open Book Qa
88 %
Trivia Qa
58 %
Wino Grande
82 %
Training Compute
213,120,000,000.00T FLOP
Phi-3-small-8k-instruct benchmark results.
Adversarial Nli Monthly
Adversarial Nli score.
Adversarial Nli Yearly
Adversarial Nli score.
Bbh Monthly
Bbh score.
Bbh Yearly
Bbh score.
Hella Swag Monthly
Hella Swag score.
Hella Swag Yearly
Hella Swag score.
Live bench Monthly
Live bench score.
Live bench Yearly
Live bench score.
Mmlu Monthly
Mmlu score.
Mmlu Yearly
Mmlu score.
Open Book Qa Monthly
Open Book Qa score.
Open Book Qa Yearly
Open Book Qa score.
Trivia Qa Monthly
Trivia Qa score.
Trivia Qa Yearly
Trivia Qa score.
Wino Grande Monthly
Wino Grande score.
Wino Grande Yearly
Wino Grande score.
Data Source
Epoch AI, 'Capabilities & Benchmarking'. Published online at epoch.ai.
Related
Phi-3.5-mini-instruct
Phi-3.5-MoE-instruct
Phi-3.5-vision-instruct
Phi-3-medium-128k-instruct
Phi-3-mini-4k-instruct
phi-4
Phi-4-mini-instruct
pixtral-large-2411
Qwen-1_8B
Qwen-14B
View all in AI Benchmarks by Model
Updates
Tutorials
Language
English
Projects
Feed
Explore
Templates
Sign in
Log In
Statistics
Templates
Feed
Public Projects
Earn
Feature Requests
Blog
Theme
Language
English
Terms
Privacy
v3.65.1