# Kimi K3 / Search Capability Leaderboard

* Search Intelligence Score: **64.2** (#29 in Search Intelligence)
* Without search: 30.6 / Lift from search +33.6
* Cost per 1K tasks: $266 (below the median score of 64.6, so not ranked on cost)
* Evaluated: Sep 22, 2026
* Lab: Moonshot AI / Weights: Open weights / Model id: moonshotai/kimi-k3

## Accuracy by benchmark

| Suite | With search | Without search |
| ----- | ----------- | -------------- |
| DSQA  | 86.5        | 44.7           |
| HLE   | 45.0        | 35.0           |
| WISER | 61.0        | 12.0           |

## Compared with

| Model                                               | Score | Lift  | Cost per 1K tasks |
| --------------------------------------------------- | ----- | ----- | ----------------- |
| Kimi K3                                             | 64.2  | +33.6 | $266              |
| [Kimi K3.1 Pro](/leaderboard/kimi-k3-1-pro)         | 74.2  | +35.5 | $268              |
| [MiMo v2.6 Pro](/leaderboard/mimo-v2-6-pro)         | 64.4  | +34.7 | $76.5             |
| [Mistral Large 4.0](/leaderboard/mistral-large-4-0) | 64.4  | +43.0 | $136              |
| [Hy4 Preview](/leaderboard/hy4-preview)             | 64.6  | +33.9 | $93.2             |

Leaderboard last updated Oct 31, 2026. Methodology: /leaderboard#methodology
