OPT-350M-Nerys-v2: benchmark results

Provider: Mr. Seeker. Access: Open.

Aggregate Rating 1128 ± 17, rank #10370 of 10916 rated models, from 68 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MMLU-by-task - High School Statistics47.22Accuracy (%)83.3
MMLU-by-task - High School Physics33.77Accuracy (%)75
MMLU-by-task - College Physics29.41Accuracy (%)71.1
MMLU-by-task - Formal Logic33.33Accuracy (%)62.9
MMLU-by-task - High School Mathematics27.41Accuracy (%)54.7
MMLU-by-task - College Chemistry32Accuracy (%)46.9
MMLU-by-task - Professional Medicine44.49Accuracy (%)42.8
MMLU-by-task - TruthfulQA MC242.08Accuracy (%)37
MMLU-by-task - High School Biology31.61Accuracy (%)33.1
MMLU-by-task - International Law37.19Accuracy (%)30.6
MMLU-by-task - High School Microeconomics29.41Accuracy (%)30.3
MMLU-by-task - High School European History28.48Accuracy (%)30.2

Interactive version: theaggregate.ai/model?slug=opt-350m-nerys-v2 · How It Works · Data refreshed daily, snapshot 2026-11-08.