kellemar-DPO-7B [bfloat16] [rev: 860ee984db0e]: benchmark results

Provider: Other.

Aggregate Rating 1423 ± 34, rank #5037 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - HellaSwag85.25Normalized accuracy (%) (10-shot)73
Open LLM Leaderboard v1 - GSM8K60.65Accuracy (%) (5-shot)72.8
Open LLM Leaderboard v1 - ARC Challenge66.21Normalized accuracy (%) (25-shot)72.7
Open LLM Leaderboard v1 - TruthfulQA MC255.53MC2 (%) (0-shot)65.3
Open LLM Leaderboard v1 - WinoGrande78.37Accuracy (%) (5-shot)62.7
Open LLM Leaderboard v1 - MMLU63.38Accuracy (%) (5-shot)60.3

Interactive version: theaggregate.ai/model?slug=kellemar-dpo-7b-bfloat16-rev-860ee984db0e · How It Works · Data refreshed daily, snapshot 2026-11-08.