delta-4B-scientific: benchmark results

Provider: Other.

Aggregate Rating 1371 ± 33, rank #7159 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - GSM8K47.08Accuracy (%) (5-shot)60.5
Open LLM Leaderboard v1 - WinoGrande75.93Accuracy (%) (5-shot)44.9
Open LLM Leaderboard v1 - ARC Challenge59.39Normalized accuracy (%) (25-shot)43.2
Open LLM Leaderboard v1 - MMLU57.56Accuracy (%) (5-shot)41.3
Open LLM Leaderboard v1 - TruthfulQA MC248.39MC2 (%) (0-shot)41
Open LLM Leaderboard v1 - HellaSwag74.1Normalized accuracy (%) (10-shot)24.3

Interactive version: theaggregate.ai/model?slug=delta-4b-scientific · How It Works · Data refreshed daily, snapshot 2026-11-08.