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

Agentic Workflow Success on τ2-bench

76.5Airline Success Rate

LongCat-Flash-Thinking-2601

13.0629.534662.47Dec 29, 2025Jan 8, 2026Jan 18, 2026Jan 28, 2026Feb 7, 2026Feb 17, 2026Feb 28, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
76.588.699.3--88.2
2026.02
7385.398--85.4
7086.298--84.7
2026.02
6979.498.2--82.2
2026.02
67.571.583.1--74
2026.02
64.785.188.6--79.5
2026.02
648286.6--77.5
2026.02
63.881.196.2--80.4
2026.02
62.581.695.8--80
2026.02
61.574.180.7--72.1
2025.12
606767.5---
6070.255.3--61.8
2026.02
59.572.284.2--72
5871.945.6--58.7
56.570.665.8--64.3
5662.348.2--55.5
2026.02
54.779.581.3--71.8
4856.942.2--49
2026.02
45.467.328.3--47
2026.02
4465.423.7--44.4
4458.845.4--49.4
2026.02
4253.326.9--40.7
2026.02
38.541.2323.4733.4555.4-
385745.6--46.9
2026.02
3653.6----
2026.02
35.555.5----
2026.02
3432.2429.1731.354.32-
2026.02
3448.1----
2026.02
31.544.312.528.9651.8-
2026.02
31.549.5632.6839.3963.31-
2026.02
31.563.617.7639.0357.19-
2026.02
30.538.623.3--30.8
2026.02
2765.3512.2836.6955.4-
2026.02
26.534.4318.4226.4450.72-
264021---
2026.02
2252.620.2--31.6
2026.02
2244.5----
2026.02
21.548.918.231.3955.4-
2026.02
2119.969.4315.8334.89-
2026.02
2022.810.5--17.7
2026.02
1930.2616.4522.5743.89-
2026.02
1949.821.8--30.2
2026.02
15.518.647.913.6735.25-
2026.02
--87--77.2
-----87.4