numfa_3b_1epoch: benchmark results

Provider: Other.

Aggregate Rating 1098 ± 38, rank #10732 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - TruthfulQA MC242.43MC2 (%) (0-shot)20.5
Open LLM Leaderboard v1 - HellaSwag37.27Normalized accuracy (%) (10-shot)7.4
Open LLM Leaderboard v1 - WinoGrande51.7Accuracy (%) (5-shot)5.9
Open LLM Leaderboard v1 - ARC Challenge25.77Normalized accuracy (%) (25-shot)5
Open LLM Leaderboard v1 - GSM8K0Accuracy (%) (5-shot)4.5
Open LLM Leaderboard v1 - MMLU24.15Accuracy (%) (5-shot)3.1

Interactive version: theaggregate.ai/model?slug=numfa-3b-1epoch · How It Works · Data refreshed daily, snapshot 2026-11-08.