#21 MoonshotAI: Kimi K3
max- Cost
- $0.281
- Time
- 506.9s
- Tokens
- 18,863 tok
Moonshot AI
Release: 2026-07-16
Tested on: 2026-07-16 17:10
moonshotai/kimi-k3::max
Summary
Kimi K3 scores 8.5 on AI BENCHY and ranks #21. It has 9.4 reliability, a 82.5% pass rate, $3.112 total cost, and 122.48s average response time.
What makes Kimi K3 unique: It stands out most in Domain specific, where it ranks #3, while Tool Calling is its weakest area at #16.
8.5
Consistency
9.2
9.4
$3.112
Total Output Tokens
200,439
Total Input Tokens
34,916
Input Price
$3.000 / 1M
Output Price
$15.000 / 1M
Flaky tests
2
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
Price History
Historical pricing data for this model from OpenRouter.
| Date | Input Price | Output Price |
|---|---|---|
| 2026-07-16 17:32 | $3.000 / 1M | $15.000 / 1M |
Charts
Choose the first model, then click a second model to open a side-by-side page.
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
Kimi K3maxvsGLM 5mediumKimi K3maxvsGPT-5 MinimediumKimi K3maxvsGLM 5.2mediumKimi K3maxvsGPT-5.4mediumKimi K3maxvsClaude Opus 4.7mediumKimi K3maxvsSeed-2.0-LitemediumKimi K3maxvsGemini 3.5 FlashhighKimi K3maxvsGemini 3 Flash PreviewmediumKimi K3maxvsNemotron 3 Ultra 550b A55bmediumFree AvailableKimi K3maxvsGPT-5.5low
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 10.0 | 10.0 | |
| Coding | 10.0 | 10.0 | |
| Combined | 10.0 | 10.0 | |
| Data parsing and extraction | 7.3 | 5.8 | |
| Domain specific | 5.9 | 7.2 | |
| General Intelligence | 10.0 | 10.0 | |
| Instructions following | 10.0 | 10.0 | |
| Puzzle Solving | 10.0 | 10.0 | |
| Tool Calling | 3.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |