Kimi K2 Base: benchmark results
Provider: Moonshot. Released 2025-07-11.
Aggregate Rating 1548 ± 48, rank #1726 of 10916 rated models, from 5 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Stats (TriviaQA) | 85.1 | Score (%) | 100 |
| LLM Stats (C-Eval) | 92.5 | Score (%) | 84.2 |
| LLM Stats Score | 12.76 | LLM Stats Score (conservative rating) | 30.7 |
| LLM Stats (CSimpleQA) | 77.6 | Score (%) | 28.6 |
| ZeroEval GPQA Diamond | 48.1 | GPQA Diamond Score | 19.5 |
Interactive version: theaggregate.ai/model?slug=kimi-k2-base · How It Works · Data refreshed daily, snapshot 2026-11-08.