Moonshot AI Kimi K2.7 Code | OpenAI GPT-5.4-Pro | |
|---|---|---|
| Overview | ||
| Company | Moonshot AI | OpenAI |
| Release date | Jun 12 2026 | Mar 5 2026 |
| Model type | — | — |
| Open source | Yes | No |
| Specifications | ||
Parameters | 1T | — |
Context window | 256k | — |
| Benchmarks | ||
Web browsing BrowseCompCan the AI browse the web and track down hard-to-find answers? Higher is better. | — | 89.3% |
Advanced math FrontierMath · Tier 1–3Very hard, research-level math problems. Tiers 1–3 are the (still extremely difficult) lower tiers. Higher is better. | — | 50% |
Advanced math FrontierMath · Tier 4Very hard, research-level math problems. Tier 4 is the hardest — close to what professional research mathematicians tackle. Higher is better. | — | 38% |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 94.4% |
Knowledge work GDPval (win/tie rate)How often the AI's work matches or beats a human expert's on real knowledge-work tasks. Higher is better. | — | 82% |
| Timeline | ||
| Release gap | GPT-5.4-Pro shipped 99 days before Kimi K2.7 Code | |
Kimi K2.7 Code and GPT-5.4-Pro don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. GPT-5.4-Pro shipped 99 days before Kimi K2.7 Code, so benchmark comparisons should account for the intervening progress.
Kimi K2.7 Code is an open-source / open-weight model; GPT-5.4-Pro is proprietary.
Direct benchmark comparisons are unavailable — Kimi K2.7 Code and GPT-5.4-Pro don't publish scores on any of the same benchmarks.