pruned-yi-3B-prerelease-ckpt01: benchmark results

Provider: Other.

Aggregate Rating 1099 ± 42, rank #10730 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - TruthfulQA MC246.05MC2 (%) (0-shot)33.2
Open LLM Leaderboard v1 - GSM8K0.08Accuracy (%) (5-shot)9.5
Open LLM Leaderboard v1 - MMLU25.18Accuracy (%) (5-shot)6.9
Open LLM Leaderboard v1 - HellaSwag31.6Normalized accuracy (%) (10-shot)6.4
Open LLM Leaderboard v1 - WinoGrande51.14Accuracy (%) (5-shot)5
Open LLM Leaderboard v1 - ARC Challenge24.4Normalized accuracy (%) (25-shot)3.6

Interactive version: theaggregate.ai/model?slug=pruned-yi-3b-prerelease-ckpt01 · How It Works · Data refreshed daily, snapshot 2026-11-08.