Franken-MoE-18B-v0.1: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1462 ± 40, rank #3188 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - ARC Challenge72.1Normalized accuracy (%) (25-shot)91
Open LLM Leaderboard v1 - HellaSwag88.3Normalized accuracy (%) (10-shot)90.8
Open LLM Leaderboard v1 - WinoGrande83.74Accuracy (%) (5-shot)90.5
Open LLM Leaderboard v1 - GSM8K69.45Accuracy (%) (5-shot)89.2
Open LLM Leaderboard v1 - TruthfulQA MC267.51MC2 (%) (0-shot)86.1
Open LLM Leaderboard v1 - MMLU65.01Accuracy (%) (5-shot)80.3

Interactive version: theaggregate.ai/model?slug=franken-moe-18b-v0-1 · How It Works · Data refreshed daily, snapshot 2026-11-08.