Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Question Answering on Pop-QA Cities 20 (Custom Metrics)

1.75Factual Accuracy

InstructLab

1.231.3651.51.635May 19, 2026
Updated 14d ago

Evaluation Results

MethodLinks
2026.05
1.751.932.76326.6
2026.05
1.731.912.762.9926.6
2026.05
1.731.922.692.9628.2
2026.05
1.681.932.532.8326.6
2026.05
1.541.942.592.967.9
2026.05
1.541.952.62.995.4
2026.05
1.3922.222.880.8
2026.05
1.352.012.142.810.8
1.251.982.152.854.2
1.251.982.152.854.2