Grok-3 mini
#114 of 274 scored.
xAIJun 24, 2025Closed
Capabilities Index
Range 137.5–142.0
140.3
Context
Tokens
—
Input
Per 1M tokens
—
Output
Per 1M tokens
—
Benchmarks
How it scores.
- GPQA Diamond68.3%
90th of 186
- ARC-AGI-20.4%
70th of 79
- Mock AIME77.8%
82nd of 176
Everything else Epoch has for it
- MATH level 590.9%
- Lech Mazur Writing73.5%
- Fiction.LiveBench66.7%
- Aider polyglot49.3%
- WeirdML42.6%
- ARC-AGI16.5%
- FrontierMath-2025-02-28-Private10.3%
On the index
Around it.
Sources