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
Public Projects
Log In
Animate this data
Bar chart race of kimi-k2-thinking, gpt-6-astra_max, gemini-3.8-flash_high and 7 more, by GPQA Diamond.
Create it free
Takes a free account
kimi-k2-thinking
Ale bench
597.50
Apex Agents
0.12 %
Cl bench
0.12 %
TerminalBench
0.36 %
WeirdML
0.43 %
Training Compute
4,200,000,000,000.00T FLOP
kimi-k2-thinking benchmark results.
Ale bench Daily
Ale bench score.
Ale bench Monthly
Ale bench score.
Ale bench Yearly
Ale bench score.
Apex Agents Daily
Apex Agents score.
Apex Agents Monthly
Apex Agents score.
Apex Agents Yearly
Apex Agents score.
Cl bench Daily
Cl bench score.
Cl bench Monthly
Cl bench score.
Cl bench Yearly
Cl bench score.
TerminalBench Daily
TerminalBench score.
TerminalBench Monthly
TerminalBench score.
TerminalBench Yearly
TerminalBench score.
WeirdML Daily
WeirdML score.
WeirdML Monthly
WeirdML score.
WeirdML Yearly
WeirdML score.
Data Source
Epoch AI, 'Capabilities & Benchmarking'. Published online at epoch.ai.
Related
kimi-k2.6
kimi-k2.6_none
kimi-k2.7-code
Kimi-K2-Instruct
Kimi-K2-Instruct-0905
kimi-k2-thinking-turbo
kimi-k3_high
kimi-k3_low
kimi-k3_max
kimi-k3_unknown
View all in AI Benchmarks by Model
Updates
Tutorials
Log In
Statistics
Templates
Public Projects
Earn
Feature Requests
Blog
Theme
Terms
Privacy
v3.55.0