GoLLIE-7B: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1172 ± 33, rank #9760 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - GSM8K3.26Accuracy (%) (5-shot)21.3
Open LLM Leaderboard v1 - MMLU29.38Accuracy (%) (5-shot)16.4
Open LLM Leaderboard v1 - ARC Challenge36.09Normalized accuracy (%) (25-shot)13.6
Open LLM Leaderboard v1 - HellaSwag57.93Normalized accuracy (%) (10-shot)13.1
Open LLM Leaderboard v1 - WinoGrande58.96Accuracy (%) (5-shot)12.1
Open LLM Leaderboard v1 - TruthfulQA MC239.27MC2 (%) (0-shot)10.6

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