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

Multimodal Agent Task on TIR-Bench

47.75Average@4

XSkill

18.8926.382533.87541.3675Mar 12, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
47.7575
2026.03
36.6262
2026.03
34.2562.5
2026.03
33.7559
2026.03
33.1258
2026.03
32.3758.5
2026.03
30.2557.5
2026.03
29.7553.5
2026.03
29.1352.5
2026.03
28.554
2026.03
28.3854
2026.03
28.2556
2026.03
27.6251
2026.03
25.552
2026.03
25.2551
2026.03
25.1353
2026.03
24.7552.5
2026.03
24.6249.5
2026.03
24.553.5
2026.03
24.2553
2026.03
23.550.5
2026.03
21.3740
2026.03
20.1345
2026.03
2046.5