Compare, 2 models
Side by side.
Claude Haiku 5.5 and Kimi K3 on every board at least two of them share. Blue marks the best in each row.
Specs
List prices, context and published output speed. Blue marks the best in each row.
| Spec | Claude Haiku 5.5Anthropic | Kimi K3Moonshot |
|---|---|---|
| Lab | Anthropic | Moonshot |
| Type | Language | Language |
| Released | Oct 7, 2026 | Jul 16, 2026 |
| Input price$ per 1M tokens | $0.10 | $3.00 |
| Output price$ per 1M tokens | $0.50 | $15.00 |
| Blended price3 input tokens per output | $0.20 | $6.00 |
| Contexttokens | 1M | 1.05M |
| Open weights | No | Yes |
| Output speedTok / s | 239 | 41 |
Benchmarks
Every board where at least two of these models have a published score. Each score links to its source.
| Board | Claude Haiku 5.5Anthropic | Kimi K3Moonshot |
|---|---|---|
| Artificial Analysis Intelligence IndexOverall, higher is better | 43Max | 44Max |
| Epoch Capabilities IndexOverall, higher is better | 159 | 158 |
| ARC-AGI-2Reasoning and knowledge, higher is better | 61.3%xhigh setting | 60.4%max setting |
| FrontierMath Tiers 1-3Reasoning and knowledge, higher is better | 75.1%max setting | 72.2%max setting |
| GPQA DiamondReasoning and knowledge, higher is better | 89.7%max setting | 93.1%max setting |
n/a means the board has not published a score for that model.