K2 [bfloat16] [rev: unknown]: benchmark results

Provider: LLM360.

Aggregate Rating 1433 ± 33, rank #4524 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - MMLU67.99Accuracy (%) (5-shot)90.3
Open LLM Leaderboard v1 - HellaSwag85.71Normalized accuracy (%) (10-shot)76.4
Open LLM Leaderboard v1 - WinoGrande80.11Accuracy (%) (5-shot)72.4
Open LLM Leaderboard v1 - ARC Challenge63.99Normalized accuracy (%) (25-shot)65.1
Open LLM Leaderboard v1 - GSM8K48.67Accuracy (%) (5-shot)61.8
Open LLM Leaderboard v1 - TruthfulQA MC240.77MC2 (%) (0-shot)15.3

Interactive version: theaggregate.ai/model?slug=k2-bfloat16-rev-unknown · How It Works · Data refreshed daily, snapshot 2026-11-08.