Kimi K2 (Jul 2025)
#116 of 274 scored.
MoonshotJul 12, 2025Open weights
Capabilities Index
Range 136.6–142.0
140.1
Context
Tokens
—
Input
Per 1M tokens
—
Output
Per 1M tokens
—
Benchmarks
How it scores.
- Terminal-Bench27.8%
27th of 35
Everything else Epoch has for it
- Lech Mazur Writing85.6%
- Fiction.LiveBench61.1%
- Aider polyglot59.1%
- WeirdML39.4%
- SimpleBench11.6%
- GSO-Bench4.9%
On the index
Around it.
Sources