K2-Chat: benchmark results
LLM360's chat fine-tune of its fully open 65B K2 model, a reproducible LLM claimed to beat Llama 2 70B Chat using 35% less compute (2024). Provider: LLM360. Released 2024-05-22. Access: Open.
Aggregate Rating 1457 ± 40, rank #3463 of 10916 rated models, from 13 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MuSR | 45.7 | Score | 86.6 |
| Enkrypt AI - Insecure Code Risk | 13.78 | Risk Score | 73.1 |
| Enkrypt AI - Risk Score | 27.61 | Risk Score | 67.2 |
| Open LLM Leaderboard - BBH | 53.58 | Score | 66.6 |
| Enkrypt AI - Jailbreak Risk | 7.04 | Risk Score | 65.8 |
| Enkrypt AI - Safety Risk | 23.94 | Risk Score | 63.3 |
| Open LLM Leaderboard - GPQA | 30.62 | Score | 63.1 |
| Open LLM Leaderboard - IFEval | 51.52 | Score | 61.4 |
| Open LLM Leaderboard - MATH Level 5 | 10.35 | Score | 48.4 |
| Open LLM Leaderboard - MMLU-Pro | 33.71 | Score | 48.1 |
| Enkrypt AI - Toxicity Risk | 5.59 | Risk Score | 28.6 |
| Enkrypt AI - Bias Risk | 87.34 | Risk Score | 24.7 |
Interactive version: theaggregate.ai/model?slug=k2-chat · How It Works · Data refreshed daily, snapshot 2026-11-08.