Brunhilde-13B: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1363 ± 35, rank #7358 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - HellaSwag83.49Normalized accuracy (%) (10-shot)59.1
Open LLM Leaderboard v1 - TruthfulQA MC252.35MC2 (%) (0-shot)55.5
Open LLM Leaderboard v1 - ARC Challenge60.49Normalized accuracy (%) (25-shot)47.9
Open LLM Leaderboard v1 - WinoGrande75.53Accuracy (%) (5-shot)42.7
Open LLM Leaderboard v1 - MMLU56.18Accuracy (%) (5-shot)38.5
Open LLM Leaderboard v1 - GSM8K9.17Accuracy (%) (5-shot)29.7

Interactive version: theaggregate.ai/model?slug=brunhilde-13b · How It Works · Data refreshed daily, snapshot 2026-11-08.