Kunoichi-DPO-v2-7B [bfloat16] [rev: d7d33a1517c5]: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1446 ± 36, rank #3940 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - HellaSwag87.42Normalized accuracy (%) (10-shot)86.1
Open LLM Leaderboard v1 - TruthfulQA MC266MC2 (%) (0-shot)84.4
Open LLM Leaderboard v1 - ARC Challenge69.37Normalized accuracy (%) (25-shot)82.9
Open LLM Leaderboard v1 - GSM8K66.03Accuracy (%) (5-shot)81.1
Open LLM Leaderboard v1 - MMLU64.83Accuracy (%) (5-shot)77.2
Open LLM Leaderboard v1 - WinoGrande80.74Accuracy (%) (5-shot)75.4

Interactive version: theaggregate.ai/model?slug=kunoichi-dpo-v2-7b-bfloat16-rev-d7d33a1517c5 · How It Works · Data refreshed daily, snapshot 2026-11-08.