Multirial: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1393 ± 33, rank #6404 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - TruthfulQA MC254.7MC2 (%) (0-shot)63.2
Open LLM Leaderboard v1 - ARC Challenge63.23Normalized accuracy (%) (25-shot)61.9
Open LLM Leaderboard v1 - GSM8K40.41Accuracy (%) (5-shot)55.7
Open LLM Leaderboard v1 - MMLU61.01Accuracy (%) (5-shot)50.5
Open LLM Leaderboard v1 - WinoGrande75.3Accuracy (%) (5-shot)41.4
Open LLM Leaderboard v1 - HellaSwag79.57Normalized accuracy (%) (10-shot)38.3

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