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 K2.5
| Claude Haiku 4.5 Anthropic | Kimi K2.5 Moonshot AI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $1.00 | $0.57 |
| Output $/1M | $5.00 | $2.85 |
| Blended $/1M (3:1) | $2.00 | $1.14 |
| Cache read $/1M | $0.10 | $0.095 |
| Cache write $/1M | $1.25 | — |
| Quality indices | ||
| Intelligence Index | 29.6 | 35.4 |
| Coding Index | 43.9 | 46.8 |
| Math Index | — | — |
| Agentic Index | 16.4 | 21.7 |
| Speed & latency | ||
| Output speed (tok/s) | — | — |
| Time to first token | — | — |
| Time to first answer token | — | — |
| Design Arena (Elo) | ||
| Website | 1,149 | 1,277 |
| Web apps | — | 1,181 |
| Full-stack | — | 1,173 |
| Mobile apps | — | 1,181 |
| Android native | — | 1,112 |
| UI components | 1,142 | 1,278 |
| Data viz | 1,160 | 1,262 |
| SVG | 1,072 | 1,193 |
| 3D | 1,131 | 1,264 |
| Game dev | 1,155 | 1,264 |
| Godot game dev | — | 1,211 |
| Code categories | 1,148 | 1,270 |
| ASCII art | 1,182 | 1,210 |
| Specs | ||
| Context window | 200K | 262K |
| Max output tokens | 64K | 262K |
| Input modalities | text, image, file | text, image |
| Tokenizer | Claude | Other |