JOSIE_Beta-3-7B-slerp: benchmark results

Provider: Other.

Aggregate Rating 1420 ± 33, rank #5172 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - WinoGrande80.43Accuracy (%) (5-shot)73.8
Open LLM Leaderboard v1 - GSM8K58.61Accuracy (%) (5-shot)70.4
Open LLM Leaderboard v1 - HellaSwag84.56Normalized accuracy (%) (10-shot)66.9
Open LLM Leaderboard v1 - MMLU64.17Accuracy (%) (5-shot)66.4
Open LLM Leaderboard v1 - ARC Challenge63.4Normalized accuracy (%) (25-shot)62.6
Open LLM Leaderboard v1 - TruthfulQA MC248.8MC2 (%) (0-shot)42.7

Interactive version: theaggregate.ai/model?slug=josie-beta-3-7b-slerp · How It Works · Data refreshed daily, snapshot 2026-11-08.