Borealis-10.7B-DPO: benchmark results

Provider: Undi95. Access: Open.

Aggregate Rating 1379 ± 33, rank #6877 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - MMLU60.74Accuracy (%) (5-shot)49.5
Open LLM Leaderboard v1 - GSM8K33.36Accuracy (%) (5-shot)49.4
Open LLM Leaderboard v1 - HellaSwag81.21Normalized accuracy (%) (10-shot)44
Open LLM Leaderboard v1 - WinoGrande75.45Accuracy (%) (5-shot)42.2
Open LLM Leaderboard v1 - ARC Challenge57.94Normalized accuracy (%) (25-shot)38.5
Open LLM Leaderboard v1 - TruthfulQA MC246.37MC2 (%) (0-shot)34.2

Interactive version: theaggregate.ai/model?slug=borealis-10-7b-dpo · How It Works · Data refreshed daily, snapshot 2026-11-08.