CharXiv-D

general

text

About

CharXiv-D benchmark

Evaluation Stats

Total Models5

Organizations1

Verified Results0

Self-Reported5

Benchmark Details

Max Score1

Language

en

Performance Overview

Score distribution and top performers

Score Distribution

5 models

Top Score

90.0%

Average Score

85.1%

High Performers (80%+)

4

Top Organizations

#1OpenAI

5 models

85.1%

Leaderboard

Top 5 models ranked by performance

1

90.0%

Raw: 0.9

Self-reported

2

88.4%

Raw: 0.884

Self-reported

3

87.9%

Raw: 0.879

Self-reported

4

85.3%

Raw: 0.853

Self-reported

5

73.9%

Raw: 0.739

Self-reported