Emerhyst-20B: benchmark results

Provider: Undi95. Access: Open.

Aggregate Rating 1371 ± 36, rank #7153 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - HellaSwag84.98Normalized accuracy (%) (10-shot)70.6
Open LLM Leaderboard v1 - TruthfulQA MC254.16MC2 (%) (0-shot)61.7
Open LLM Leaderboard v1 - ARC Challenge61.69Normalized accuracy (%) (25-shot)53.9
Open LLM Leaderboard v1 - WinoGrande76.09Accuracy (%) (5-shot)45.9
Open LLM Leaderboard v1 - MMLU56.98Accuracy (%) (5-shot)40.3
Open LLM Leaderboard v1 - GSM8K8.49Accuracy (%) (5-shot)28.5

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