1 vs 1 benchmarks won
Moonshot AI Kimi K2.6 | OpenAI GPT-5.2 | |
|---|---|---|
| Overview | ||
| Company | Moonshot AI | OpenAI |
| Release date | Apr 21 2026 | Dec 11 2025 |
| Model type | — | — |
| Open source | Yes | No |
| Specifications | ||
Parameters | 1T | — |
Context window | 256k | — |
| Benchmarks | ||
Coding SWE-Bench VerifiedReal coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 80.2%Best | 80% |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 90.5% | 92.4%Best |
| Timeline | ||
| Release gap | GPT-5.2 shipped 131 days before Kimi K2.6 | |
Kimi K2.6 and GPT-5.2 are evenly matched across the 2 benchmarks they both report (SWE-Bench Verified, GPQA Diamond). GPT-5.2 shipped 131 days before Kimi K2.6, so benchmark comparisons should account for the intervening progress.
Kimi K2.6 is an open-source / open-weight model; GPT-5.2 is proprietary.
On SWE-Bench Verified, Kimi K2.6 leads at 80.2% vs GPT-5.2 at 80%. On GPQA Diamond, GPT-5.2 leads at 92.4% vs Kimi K2.6 at 90.5%.