Wernicke-7B-dpo: benchmark results

Provider: CultriX. Access: Open.

Aggregate Rating 1464 ± 41, rank #3090 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - TruthfulQA MC273.91MC2 (%) (0-shot)94.6
Open LLM Leaderboard v1 - WinoGrande84.61Accuracy (%) (5-shot)94
Open LLM Leaderboard v1 - HellaSwag88.63Normalized accuracy (%) (10-shot)93.2
Open LLM Leaderboard v1 - ARC Challenge71.84Normalized accuracy (%) (25-shot)90.3
Open LLM Leaderboard v1 - GSM8K67.63Accuracy (%) (5-shot)84
Open LLM Leaderboard v1 - MMLU65.22Accuracy (%) (5-shot)83.1

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