Saraa-8B-ORPO-AUNQA-16bit: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1408 ± 33, rank #5728 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - MMLU65.47Accuracy (%) (5-shot)84.5
Open LLM Leaderboard v1 - WinoGrande78.3Accuracy (%) (5-shot)62
Open LLM Leaderboard v1 - GSM8K43.97Accuracy (%) (5-shot)58.1
Open LLM Leaderboard v1 - HellaSwag81.86Normalized accuracy (%) (10-shot)47.4
Open LLM Leaderboard v1 - ARC Challenge59.13Normalized accuracy (%) (25-shot)42.2
Open LLM Leaderboard v1 - TruthfulQA MC248.25MC2 (%) (0-shot)40.4

Interactive version: theaggregate.ai/model?slug=saraa-8b-orpo-aunqa-16bit · How It Works · Data refreshed daily, snapshot 2026-11-08.