MiniMerlin-3B: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1267 ± 34, rank #9099 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - GSM8K20.17Accuracy (%) (5-shot)41.1
Open LLM Leaderboard v1 - TruthfulQA MC247.07MC2 (%) (0-shot)36.4
Open LLM Leaderboard v1 - MMLU43.21Accuracy (%) (5-shot)22.5
Open LLM Leaderboard v1 - ARC Challenge44.37Normalized accuracy (%) (25-shot)20
Open LLM Leaderboard v1 - HellaSwag66.56Normalized accuracy (%) (10-shot)17.8
Open LLM Leaderboard v1 - WinoGrande64.4Accuracy (%) (5-shot)17.3

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