Compare models
Pick up to 4 models for a side-by-side spec sheet. Hover any dotted metric name for what the test measures. Best value in each row is highlighted.
Claude Haiku 4.5Kimi K3
| Claude Haiku 4.5 Anthropic | Kimi K3 Moonshot AI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $1.00 | $1.70 |
| Output $/1M | $5.00 | $8.50 |
| Blended $/1M (3:1) | $2.00 | $3.40 |
| Cache read $/1M | $0.10 | $0.17 |
| Cache write $/1M | $1.25 | — |
| Quality indices | ||
| Intelligence Index | 16.9 | 43.6 |
| Coding Index | 43.9 | 76.2 |
| Math Index | — | — |
| Agentic Index | 8 | 50 |
| Speed & latency | ||
| Output speed (tok/s) | — | — |
| Time to first token | — | — |
| Time to first answer token | — | — |
| Design Arena (Elo) | ||
| Website | 1,135 | 1,352 |
| Web apps | — | 1,309 |
| Full-stack | — | 1,333 |
| Mobile apps | — | 1,279 |
| Android native | — | 1,259 |
| UI components | 1,115 | 1,371 |
| Data viz | 1,139 | 1,358 |
| SVG | 1,049 | 1,330 |
| 3D | 1,101 | 1,425 |
| Game dev | 1,120 | 1,407 |
| Agentic game dev | — | 1,252 |
| Godot game dev | — | 1,199 |
| HTML slides | — | 1,259 |
| Python→PPTX slides | — | 1,273 |
| Code categories | 1,130 | 1,386 |
| ASCII art | 1,159 | — |
| Specs | ||
| Context window | 200K | 1.05M |
| Max output tokens | 64K | 944K |
| Input modalities | text, image, file | text, image, video |
| Tokenizer | Claude | Other |