moonshotai / kimi family
kimi-k2-thinking-0905
moonshotai/kimi-k2-thinking-0905
Benchmarks
Where it scores.
General Provisional
81.6
Coding Provisional
67.0
Math Provisional
73.6
Reasoning Provisional
69.7
Normalized 0–100 across indexed models.
Runnable variants
Pick a size.
No recommended variants are indexed for this model.
Raw benchmarks
The inputs.
| Source | Task | Raw | Normalized |
|---|---|---|---|
| ZeroEval | AIME2025 | 100.0 | 100.0 |
| ZeroEval | GPQA | 84.5 | 84.5 |
| ZeroEval | HLE | 51.0 | 51.0 |
| ZeroEval | SWEBenchVerified | 71.3 | 71.3 |
| ZeroEval | SciCode | 44.8 | 44.8 |
From the Hugging Face model card
About this model.
From the Hugging Face model card