0.001_idpo_declr_4iters_iter_2: benchmark results

Provider: Other.

Aggregate Rating 1393 ± 33, rank #6405 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - HellaSwag84.81Normalized accuracy (%) (10-shot)68.9
Open LLM Leaderboard v1 - ARC Challenge62.46Normalized accuracy (%) (25-shot)58
Open LLM Leaderboard v1 - WinoGrande77.58Accuracy (%) (5-shot)57
Open LLM Leaderboard v1 - MMLU61.11Accuracy (%) (5-shot)50.8
Open LLM Leaderboard v1 - GSM8K27.82Accuracy (%) (5-shot)45.5
Open LLM Leaderboard v1 - TruthfulQA MC248.18MC2 (%) (0-shot)40.1

Interactive version: theaggregate.ai/model?slug=0-001-idpo-declr-4iters-iter-2 · How It Works · Data refreshed daily, snapshot 2026-11-08.