robin-65B-v2-delta: benchmark results

Provider: Other.

Aggregate Rating 1380 ± 18, rank #6846 of 10916 rated models, from 62 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MMLU-by-task - Computer Security79Accuracy (%)99.1
MMLU-by-task - College Physics38.24Accuracy (%)95.3
MMLU-by-task - Virology53.01Accuracy (%)94.1
MMLU-by-task - US Foreign Policy87Accuracy (%)93.2
MMLU-by-task - Sociology85.57Accuracy (%)93.1
MMLU-by-task - Anatomy56.3Accuracy (%)92.3
MMLU-by-task - Public Relations70Accuracy (%)92
MMLU-by-task - College Medicine58.96Accuracy (%)91.5
MMLU-by-task - Prehistory73.15Accuracy (%)91.5
MMLU-by-task - Philosophy71.06Accuracy (%)91.3
MMLU-by-task - Professional Psychology66.67Accuracy (%)91.3
MMLU-by-task - Marketing86.75Accuracy (%)91

Interactive version: theaggregate.ai/model?slug=robin-65b-v2-delta · How It Works · Data refreshed daily, snapshot 2026-11-08.