orca-mini-v5.8B-dpo: benchmark results

Provider: Other. Access: Open.

Unified ELO 1475 ± 19, rank #1512 of 2928 rated models, from 12 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - GSM8K67.7Accuracy (%) (5-shot)84.2
Open LLM Leaderboard v1 - MMLU65.1Accuracy (%) (5-shot)81.7
Open LLM Leaderboard v1 - TruthfulQA MC256.24MC2 (%) (0-shot)67.4
Open LLM Leaderboard - IFEval48.96Score57.2
Open LLM Leaderboard v1 - ARC Challenge61.86Normalized accuracy (%) (25-shot)54.8
Open LLM Leaderboard - BBH50.75Score52
Open LLM Leaderboard v1 - HellaSwag82.35Normalized accuracy (%) (10-shot)50.7
Open LLM Leaderboard - MATH Level 59.74Score46.5
Open LLM Leaderboard - MMLU-Pro31.16Score40.7
Open LLM Leaderboard - MuSR38.94Score34.8
Open LLM Leaderboard v1 - WinoGrande73.4Accuracy (%) (5-shot)31.9
Open LLM Leaderboard - GPQA27.43Score29.4

Interactive version: theaggregate.ai/model?slug=orca-mini-v5-8b-dpo · How It Works · Data refreshed daily, snapshot 2026-09-23.