Kimi is Moonshot AI’s long-context model family. The Kimi K2 series ships under permissive open weights and leads many open agent leaderboards on tool-use and reasoning benchmarks.
See all models from Moonshot AIModels in family
6
Open weight
6
API only
0
Avg score
57.3
Top benchmark
97.1
MATH-500
Total HF downloads
2.5M
Primary modality
Text
Context window
128K – 262K
First release
Jul 2025
Latest release
Jun 2026
Every release in the Kimi family, ranked by composite score across benchmarks, popularity, efficiency, and versatility.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | text | BB68.8 | 1.0T | Apr 2026 | |
| 2 | text | BB67.5 | 1.0T | Jan 2026 | |
| 3 | text | BB56.9 | 1.0T | Jun 2026 | |
| 4 | text | CC53.9 | 1.0T | Jul 2025 | |
| 5 | text | CC51.9 | 1.0T | Oct 2025 | |
| 6 | text | CC44.5 | 1.0T | Sep 2025 |
When each release shipped, newest first. Useful for tracking version cadence.
Jun 12
Apr 20
Jan 26
Oct 31
Jul 10
Composite grades across this family. Higher is better, blending benchmarks, popularity, and efficiency.
Models with downloadable weights, ranked by composite score.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | text | BB68.8 | 1.0T | Apr 2026 | |
| 2 | text | BB67.5 | 1.0T | Jan 2026 | |
| 3 | text | BB56.9 | 1.0T | Jun 2026 | |
| 4 | text | CC53.9 | 1.0T | Jul 2025 | |
| 5 | text | CC51.9 | 1.0T | Oct 2025 | |
| 6 | text | CC44.5 | 1.0T | Sep 2025 |
The Kimi family is a series of AI models from Moonshot AI. This page lists every release in the family with its benchmark scores, parameter count, and hardware requirements.
By composite score, Kimi K2.6 is currently the top model in the family. For local inference, match the parameter count to your VRAM budget. For quality, pick the highest scorer that fits.
See the open-weight section above for models you can run locally. The API-only section lists closed releases that must be accessed through the provider’s API.
Spin up an instance in the cloud, or pick local hardware that fits.
Full Directory
Open the full directory to filter by hardware, capability, license, and benchmark score.
Or Browse by Provider
See every model from a lab side by side, with aggregate stats. Useful when you want a cross-family view of one provider.
