kuno-kunoichi-v1-DPO-v2-SLERP-7B: benchmark results

Provider: grimjim. Access: Open.

Aggregate Rating 1446 ± 36, rank #3963 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - HellaSwag87.33Normalized accuracy (%) (10-shot)85.6
Open LLM Leaderboard v1 - TruthfulQA MC265.12MC2 (%) (0-shot)83.1
Open LLM Leaderboard v1 - GSM8K66.72Accuracy (%) (5-shot)82.3
Open LLM Leaderboard v1 - ARC Challenge69.11Normalized accuracy (%) (25-shot)82.2
Open LLM Leaderboard v1 - MMLU64.8Accuracy (%) (5-shot)76.8
Open LLM Leaderboard v1 - WinoGrande80.9Accuracy (%) (5-shot)76.2

Interactive version: theaggregate.ai/model?slug=kuno-kunoichi-v1-dpo-v2-slerp-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.