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 Baichuan, Google DeepMind, OpenAI and 7 more, by GPQA Diamond.
Create it free
Takes a free account
Baichuan
Bbh
49 %
Bool Q
67 %
Gsm8k
53 %
Hella Swag
71 %
Lambada
74 %
Mmlu
59 %
Piqa
78 %
Training Compute
203,000,000,000.00T FLOP
Baichuan benchmark results over time.
Bbh Monthly
Bbh score.
Bbh Yearly
Bbh score.
Bool Q Monthly
Bool Q score.
Bool Q Yearly
Bool Q score.
Gsm8k Monthly
Gsm8k score.
Gsm8k Yearly
Gsm8k score.
Hella Swag Monthly
Hella Swag score.
Hella Swag Yearly
Hella Swag score.
Lambada Monthly
Lambada score.
Lambada Yearly
Lambada score.
Mmlu Monthly
Mmlu score.
Mmlu Yearly
Mmlu score.
Piqa Monthly
Piqa score.
Piqa Yearly
Piqa score.
Data Source
Epoch AI, 'Capabilities & Benchmarking'. Published online at epoch.ai.
Related
Allen Institute for AI
Amazon
Ant Group
Anthropic
Arcee AI
Cerebras Systems
Cognition
Cohere
Cursor
Databricks
View all in AI Benchmarks by Organization
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