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

Conversation Evaluation on Braceval

70.8Accuracy

Gemini-3 Pro

31.17641.46351.7562.037Mar 10, 2026
Updated 2mo ago

Evaluation Results

MethodLinks
2026.03
70.8
2026.03
68.1
2026.03
66
2026.03
65.6
2026.03
60.8
2026.03
60.2
2026.03
59
2026.03
56.9
2026.03
56.3
2026.03
55.8
2026.03
53.8
2026.03
50.9
2026.03
50.2
2026.03
44.6
2026.03
32.7