bagel-dpo-34B-v0.2 [float16] [rev: fcc6ada5ea6d]: benchmark results

Provider: Jon Durbin. Access: Open.

Aggregate Rating 1503 ± 34, rank #2290 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - MMLU76.58Accuracy (%) (5-shot)97.6
Open LLM Leaderboard v1 - ARC Challenge71.93Normalized accuracy (%) (25-shot)90.5
Open LLM Leaderboard v1 - TruthfulQA MC270.05MC2 (%) (0-shot)89.9
Open LLM Leaderboard v1 - WinoGrande83.35Accuracy (%) (5-shot)88.4
Open LLM Leaderboard v1 - GSM8K60.96Accuracy (%) (5-shot)73.3
Open LLM Leaderboard v1 - HellaSwag85.25Normalized accuracy (%) (10-shot)73

Interactive version: theaggregate.ai/model?slug=bagel-dpo-34b-v0-2-float16-rev-fcc6ada5ea6d · How It Works · Data refreshed daily, snapshot 2026-11-08.