SOLAR-DUS-implement: benchmark results

Provider: Upstage. Access: Open.

Aggregate Rating 1391 ± 34, rank #6476 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - MMLU63.68Accuracy (%) (5-shot)62.4
Open LLM Leaderboard v1 - WinoGrande76.48Accuracy (%) (5-shot)48.5
Open LLM Leaderboard v1 - GSM8K26.99Accuracy (%) (5-shot)45
Open LLM Leaderboard v1 - HellaSwag81.18Normalized accuracy (%) (10-shot)43.9
Open LLM Leaderboard v1 - ARC Challenge59.56Normalized accuracy (%) (25-shot)43.8
Open LLM Leaderboard v1 - TruthfulQA MC240.72MC2 (%) (0-shot)15.1

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