0.0_withdpo_4iters_bs256_531lr_iter_3: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1386 ± 34, rank #6668 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - HellaSwag84.92Normalized accuracy (%) (10-shot)70.2
Open LLM Leaderboard v1 - TruthfulQA MC252.64MC2 (%) (0-shot)56.8
Open LLM Leaderboard v1 - ARC Challenge61.69Normalized accuracy (%) (25-shot)53.9
Open LLM Leaderboard v1 - WinoGrande77.03Accuracy (%) (5-shot)52.7
Open LLM Leaderboard v1 - MMLU60.28Accuracy (%) (5-shot)47.5
Open LLM Leaderboard v1 - GSM8K15.77Accuracy (%) (5-shot)37.6

Interactive version: theaggregate.ai/model?slug=0-0-withdpo-4iters-bs256-531lr-iter-3 · How It Works · Data refreshed daily, snapshot 2026-11-08.