Head-to-head · 2 models compared
Kimi vs DeepSeek
Moonshot AI and DeepSeek between them account for 2 rated models on the OpenRating Index. Kimi's strongest entry is Kimi K3 (max) at 59.8, against DeepSeek's DeepSeek V4 Pro 0813 (max) at 53.4. Both are scored on the same axes, with the same tests, below.
Who wins on each axis
Kimi takes 1 of 3 axes, DeepSeek takes 2.
OpenRating Index
Kimi
59.8
Kimi: Kimi K3 (max) · composite 0–100
Output speed
DeepSeek
82 tok/s
DeepSeek: DeepSeek V4 Pro 0813 (max) · blended tok/s, fastest model
Cost / task
DeepSeek
$0.25
DeepSeek: DeepSeek V4 Pro 0813 (max) · lowest model, per benchmark run
Every rated model, side by side
Sorted by OpenRating Index. Every figure is measured under the same standardised workload.
| Model | Provider | Index | Reasoning | Speed | Cost / task | Input / 1M |
|---|---|---|---|---|---|---|
| Kimi K3 (max) | Kimi | 59.8 | 85.5 | 38 tok/s | $0.84 | $0.9 |
| DeepSeek V4 Pro 0813 (max) | DeepSeek | 53.4 | 75.2 | 82 tok/s | $0.25 | $0.22 |
Put Kimi and DeepSeek head to head yourself
Pick any combination of models and compare their full cost breakdown — reasoning, answer generation, cache overhead, and input payload — in the OpenRating comparison tool.
Open the comparison tool →