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

Open-ended query evaluation on Arena-Hard-Auto v0.1

31.5Win Rate

S-SPPO

11.84416.94722.0527.153Jun 1, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.06
31.5
2026.06
31
2026.06
30.6
2026.06
30.1
2026.06
30
2026.06
29.8
2026.06
23.9
2026.06
23.3
2026.06
21.8
2026.06
21.5
2026.06
20.7
2026.06
20.4
2026.06
18.7
2026.06
12.6