GML-Mistral-merged-v1 (Publisher: zyh3826): benchmark results

Provider: Other.

Aggregate Rating 1453 ± 37, rank #3651 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - TruthfulQA MC269.28MC2 (%) (0-shot)88.7
Open LLM Leaderboard v1 - ARC Challenge71.25Normalized accuracy (%) (25-shot)88.6
Open LLM Leaderboard v1 - HellaSwag87.88Normalized accuracy (%) (10-shot)88.5
Open LLM Leaderboard v1 - MMLU65.42Accuracy (%) (5-shot)84.3
Open LLM Leaderboard v1 - GSM8K64.97Accuracy (%) (5-shot)79.3
Open LLM Leaderboard v1 - WinoGrande80.98Accuracy (%) (5-shot)76.5

Interactive version: theaggregate.ai/model?slug=gml-mistral-merged-v1-publisher-zyh3826 · How It Works · Data refreshed daily, snapshot 2026-11-08.