Brunhilde-13B-v3: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1357 ± 37, rank #7532 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - HellaSwag84.02Normalized accuracy (%) (10-shot)63.2
Open LLM Leaderboard v1 - TruthfulQA MC252.99MC2 (%) (0-shot)58.1
Open LLM Leaderboard v1 - ARC Challenge60.15Normalized accuracy (%) (25-shot)46.6
Open LLM Leaderboard v1 - WinoGrande74.27Accuracy (%) (5-shot)35.8
Open LLM Leaderboard v1 - MMLU55.03Accuracy (%) (5-shot)35.2
Open LLM Leaderboard v1 - GSM8K1.44Accuracy (%) (5-shot)17

Interactive version: theaggregate.ai/model?slug=brunhilde-13b-v3 · How It Works · Data refreshed daily, snapshot 2026-11-08.