UltraMerge-7B: benchmark results

Provider: mlabonne. Access: Open.

Aggregate Rating 1469 ± 36, rank #2859 of 10916 rated models, from 7 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - HellaSwag89.25Normalized accuracy (%) (10-shot)98.7
Open LLM Leaderboard v1 - TruthfulQA MC278.17MC2 (%) (0-shot)98.7
Open LLM Leaderboard v1 - WinoGrande84.85Accuracy (%) (5-shot)95.5
Open LLM Leaderboard v1 - ARC Challenge73.04Normalized accuracy (%) (25-shot)95.2
Open LLM Leaderboard v1 - GSM8K69.22Accuracy (%) (5-shot)88.4
YALL Nous Leaderboard56.95Average76.6
Open LLM Leaderboard v1 - MMLU64.4Accuracy (%) (5-shot)69.7

Interactive version: theaggregate.ai/model?slug=ultramerge-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.