xAI's Grok and Moonshot AI's Kimi, compared through their current models on the Respan Index. The strongest Grok model today is Grok 4.6 (#19 on the Respan Index, 51.0); the strongest Kimi model is Kimi K3 (#21, 50.6). Grok's best models lead in coding, agents, reasoning and knowledge; Kimi's lead in human preference.
| Category | Grok | Kimi |
|---|---|---|
| coding | Grok 4.7 43.2 | Kimi K3 37.2 |
| agents | Grok 4.7 65.6 | Kimi K3 63.1 |
| reasoning | Grok 4.6 51.7 | Kimi K3 47.0 |
| knowledge | Grok 4.7 55.7 | Kimi K3 52.7 |
| human preference | Grok 4.7 56.0 | Kimi K3 56.7 |
Each family's highest Respan Index category score; the higher one is bold. * Estimated: no published scores in that category.
Respan Index rank and score, blended list price per 1M tokens.
Respan Index rank and score, blended list price per 1M tokens.
The cheapest ranked Grok model is Grok 4.1 Fast Reasoning at $0.275 per 1M tokens blended; the cheapest Kimi model is Kimi K2.6 at $1.71.