0.0001_withdpo_4iters_bs256_5102lr_iter_4: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1388 ± 34, rank #6599 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - HellaSwag84.88Normalized accuracy (%) (10-shot)69.7
Open LLM Leaderboard v1 - WinoGrande77.58Accuracy (%) (5-shot)57
Open LLM Leaderboard v1 - ARC Challenge61.95Normalized accuracy (%) (25-shot)55.2
Open LLM Leaderboard v1 - TruthfulQA MC251.71MC2 (%) (0-shot)53
Open LLM Leaderboard v1 - MMLU60.46Accuracy (%) (5-shot)48.2
Open LLM Leaderboard v1 - GSM8K17.06Accuracy (%) (5-shot)38.6

Interactive version: theaggregate.ai/model?slug=0-0001-withdpo-4iters-bs256-5102lr-iter-4 · How It Works · Data refreshed daily, snapshot 2026-11-08.