COLLIE

general

text

About

COLLIE benchmark

Evaluation Stats

Total Models7

Organizations1

Verified Results0

Self-Reported7

Benchmark Details

Max Score1

Language

en

Performance Overview

Score distribution and top performers

Score Distribution

7 models

Top Score

99.0%

Average Score

70.6%

High Performers (80%+)

2

Top Organizations

#1OpenAI

7 models

70.6%

Leaderboard

Top 7 models ranked by performance

1

99.0%

Raw: 0.99

Self-reported

2

98.7%

Raw: 0.987

Self-reported

3

72.3%

Raw: 0.723

Self-reported

4

65.8%

Raw: 0.658

Self-reported

5

61.0%

Raw: 0.61

Self-reported

6

54.6%

Raw: 0.546

Self-reported

7

42.5%

Raw: 0.425

Self-reported