StrangeMerges_46-7B-dare_ties: benchmark results

Provider: Gille. Access: Open.

Aggregate Rating 1426 ± 36, rank #4861 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - TruthfulQA MC265.17MC2 (%) (0-shot)83.2
Open LLM Leaderboard v1 - HellaSwag86.4Normalized accuracy (%) (10-shot)80.8
Open LLM Leaderboard v1 - ARC Challenge67.24Normalized accuracy (%) (25-shot)76.2
Open LLM Leaderboard v1 - GSM8K59.29Accuracy (%) (5-shot)71.1
Open LLM Leaderboard v1 - WinoGrande79.48Accuracy (%) (5-shot)69.4
Open LLM Leaderboard v1 - MMLU62.17Accuracy (%) (5-shot)54.3

Interactive version: theaggregate.ai/model?slug=strangemerges-46-7b-dare-ties · How It Works · Data refreshed daily, snapshot 2026-11-08.