StrangeMerges_40-7B-dare_ties: benchmark results

Provider: Gille. Access: Open.

Aggregate Rating 1463 ± 42, rank #3119 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - TruthfulQA MC277.21MC2 (%) (0-shot)96.7
Open LLM Leaderboard v1 - ARC Challenge73.04Normalized accuracy (%) (25-shot)95.2
Open LLM Leaderboard v1 - HellaSwag88.62Normalized accuracy (%) (10-shot)93.1
Open LLM Leaderboard v1 - WinoGrande83.98Accuracy (%) (5-shot)91.5
Open LLM Leaderboard v1 - GSM8K68.01Accuracy (%) (5-shot)84.9
Open LLM Leaderboard v1 - MMLU64.59Accuracy (%) (5-shot)73.1

Interactive version: theaggregate.ai/model?slug=strangemerges-40-7b-dare-ties · How It Works · Data refreshed daily, snapshot 2026-11-08.