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 gpt-5-mini-2025-08-07_medium, gpt-6-astra_max, gemini-3.8-flash_high and 7 more, by GPQA Diamond.
Create it free
Takes a free account
gpt-5-mini-2025-08-07_medium
Arc Agi
0.37 %
Arc Agi 2
0.04 %
FrontierMath
0.20 %
FrontierMath Tier 4
0.04 %
GPQA Diamond
0.72 %
Lech Mazur Writing
0.08 %
Math Level 5
0.97 %
Mystery Game Puzzles
0.04 %
OTIS Mock AIME 2024 2025
0.78 %
SWE bench Verified
0.65 %
TerminalBench
0.32 %
gpt-5-mini-2025-08-07_medium benchmark results.
Arc Agi Daily
Arc Agi score.
Arc Agi Monthly
Arc Agi score.
Arc Agi Yearly
Arc Agi score.
Arc Agi 2 Daily
Arc Agi 2 score.
Arc Agi 2 Monthly
Arc Agi 2 score.
Arc Agi 2 Yearly
Arc Agi 2 score.
FrontierMath Daily
FrontierMath score.
FrontierMath Monthly
FrontierMath score.
FrontierMath Yearly
FrontierMath score.
FrontierMath Tier 4 Daily
FrontierMath Tier 4 score.
FrontierMath Tier 4 Monthly
FrontierMath Tier 4 score.
FrontierMath Tier 4 Yearly
FrontierMath Tier 4 score.
GPQA Diamond Daily
GPQA Diamond score.
GPQA Diamond Monthly
GPQA Diamond score.
GPQA Diamond Yearly
GPQA Diamond score.
Lech Mazur Writing Daily
Lech Mazur Writing score.
Lech Mazur Writing Monthly
Lech Mazur Writing score.
Lech Mazur Writing Yearly
Lech Mazur Writing score.
Math Level 5 Daily
Math Level 5 score.
Math Level 5 Monthly
Math Level 5 score.
Math Level 5 Yearly
Math Level 5 score.
Mystery Game Puzzles Daily
Mystery Game Puzzles score.
Mystery Game Puzzles Monthly
Mystery Game Puzzles score.
Mystery Game Puzzles Yearly
Mystery Game Puzzles score.
OTIS Mock AIME 2024 2025 Daily
OTIS Mock AIME 2024 2025 score.
OTIS Mock AIME 2024 2025 Monthly
OTIS Mock AIME 2024 2025 score.
OTIS Mock AIME 2024 2025 Yearly
OTIS Mock AIME 2024 2025 score.
SWE bench Verified Daily
SWE bench Verified score.
SWE bench Verified Monthly
SWE bench Verified score.
SWE bench Verified Yearly
SWE bench Verified score.
TerminalBench Daily
TerminalBench score.
TerminalBench Monthly
TerminalBench score.
TerminalBench Yearly
TerminalBench score.
Data Source
Epoch AI, 'Capabilities & Benchmarking'. Published online at epoch.ai.
Related
gpt-5.6-terra_xhigh
gpt-5-codex
gpt-5-codex_high
gpt-5-mini-2025-08-07_high
gpt-5-mini-2025-08-07_low
gpt-5-mini-2025-08-07_minimal
gpt-5-mini-2025-08-07_unknown
gpt-5-nano-2025-08-07_high
gpt-5-nano-2025-08-07_low
gpt-5-nano-2025-08-07_medium
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