guanaco-33B-merged: benchmark results

Provider: Other.

Aggregate Rating 1324 ± 18, rank #8273 of 10916 rated models, from 62 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MMLU-by-task - Econometrics36.84Accuracy (%)88.3
MMLU-by-task - HellaSwag64.47Accuracy (%)87.6
MMLU-by-task - Professional Medicine58.09Accuracy (%)87
MMLU-by-task - College Physics34.31Accuracy (%)86.4
MMLU-by-task - College Mathematics37Accuracy (%)85.2
MMLU-by-task - ARC Challenge58.7Accuracy (%)85
MMLU-by-task - High School European History72.12Accuracy (%)84.8
MMLU-by-task - High School US History77.94Accuracy (%)83.8
MMLU-by-task - College Chemistry43Accuracy (%)83.5
MMLU-by-task - High School World History76.79Accuracy (%)82.9
MMLU-by-task - Medical Genetics62Accuracy (%)82.4
MMLU-by-task - Abstract Algebra34Accuracy (%)82

Interactive version: theaggregate.ai/model?slug=guanaco-33b-merged · How It Works · Data refreshed daily, snapshot 2026-11-08.