Psydestroyer-20B: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1364 ± 37, rank #7336 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - HellaSwag85.17Normalized accuracy (%) (10-shot)72.3
Open LLM Leaderboard v1 - TruthfulQA MC254.83MC2 (%) (0-shot)63.6
Open LLM Leaderboard v1 - ARC Challenge60.32Normalized accuracy (%) (25-shot)47.1
Open LLM Leaderboard v1 - MMLU55.56Accuracy (%) (5-shot)36.6
Open LLM Leaderboard v1 - WinoGrande74.27Accuracy (%) (5-shot)35.8
Open LLM Leaderboard v1 - GSM8K0.08Accuracy (%) (5-shot)9.5

Interactive version: theaggregate.ai/model?slug=psydestroyer-20b · How It Works · Data refreshed daily, snapshot 2026-11-08.