merlin1.4: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1365 ± 33, rank #7310 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - GSM8K48.45Accuracy (%) (5-shot)61.6
Open LLM Leaderboard v1 - ARC Challenge59.3Normalized accuracy (%) (25-shot)42.8
Open LLM Leaderboard v1 - WinoGrande74.98Accuracy (%) (5-shot)39.7
Open LLM Leaderboard v1 - MMLU56.34Accuracy (%) (5-shot)38.8
Open LLM Leaderboard v1 - TruthfulQA MC247.36MC2 (%) (0-shot)37.5
Open LLM Leaderboard v1 - HellaSwag74.5Normalized accuracy (%) (10-shot)24.7

Interactive version: theaggregate.ai/model?slug=merlin1-4 · How It Works · Data refreshed daily, snapshot 2026-11-08.