by Moonshot AI
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. Kimi K2 excels across a broad range of benchmarks, particularly in coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) tasks. It supports long-context inference up to 128K tokens and is designed with a novel training stack that includes the MuonClip optimizer for stable large-scale MoE training.
| Signal | Strength | Weight | Impact |
|---|---|---|---|
| Recency2026-03-03T20:28:12.913Z | 90 | 15% | +13.5 |
| Context Window2026-03-03T20:28:12.913Z | 81 | 15% | +12.2 |
| Capabilities2026-03-03T20:28:12.913Z | 43 | 25% | +10.7 |
| Versatility2026-03-03T20:28:12.913Z | 33 | 10% | +3.3 |
| Output Capacity2026-03-03T20:28:12.913Z | 20 | 10% | +2.0 |
| Pricing Tier2026-03-03T20:28:12.913Z | 2 | 25% | +0.6 |
Cost Estimator
You save $30.34/month vs category average