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

Tool-use Reasoning on ShopTrajQA 32k context

62.6Accuracy

gpt-oss-120B

11.84825.02438.251.376Jun 6, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
62.6
2026.06
62.5
2026.06
59.2
2026.06
48
2026.06
38.4
2026.06
36.4
2026.06
28.7
2026.06
28.1
2026.06
25
2026.06
23
2026.06
22.3
2026.06
17.3
2026.06
17.1
2026.06
13.8