2 vs 0 benchmarks won
Moonshot AI Kimi K2 | xAI Grok 4.3 Beta | |
|---|---|---|
| Overview | ||
| Company | Moonshot AI | xAI |
| Release date | Jul 11 2025 | Apr 17 2026 |
| Model type | — | — |
| Open source | Yes | No |
| Specifications | ||
Parameters | 1T | — |
Context window | 128k | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | 75.1% | — |
Software engineering SWE-Bench Verified | 65.8% | — |
Multimodal understanding MMMU | — | — |
| Timeline | ||
| Release gap | Kimi K2 shipped 280 days before Grok 4.3 Beta | |
Kimi K2 leads Grok 4.3 Beta on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Kimi K2 shipped 280 days before Grok 4.3 Beta, so benchmark comparisons should account for the intervening progress.
Kimi K2 is an open-source / open-weight model; Grok 4.3 Beta is proprietary.
Direct benchmark comparisons are unavailable — at least one of these models has not published scores on GPQA Diamond, SWE-Bench Verified, or MMMU.