Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Interactive Tool-Use Agent Performance on tau2-Bench (Retail, Airline, Telecom)

81.1Retail Performance Score

GPT-5-think

4.03624.04344.0564.057Dec 28, 2025Jan 4, 2026Jan 11, 2026Jan 19, 2026Jan 26, 2026Feb 2, 2026Feb 10, 2026
Updated 4d ago

Evaluation Results

MethodLinks
81.162.696.784.2-
2025.12
81.162.696.7--
2026.02
80.264.858.268.4-
2025.12
80.264.858.2--
2026.02
77.25691.279.1-
2026.01
77.27245.6--
2025.12
74.86276.3--
2026.01
74.166.544.7-2.8
2026.02
71.958.647.3--
2026.02
71.95845.658.6-
2025.12
71.95845.6--
2026.01
71.16329-9.5
2026.01
70.865.544.7--
2026.02
70.656.565.8--
2026.02
70.656.565.866.1-
2025.12
70.656.565.8--
2026.01
70.46542.1-7.3
70.25646.557.9-
2026.02
70.26055.362.3-
2026.01
70.25428.9--
2026.01
70.26443.9-2.5
2025.12
70.25646.5--
2025.12
70.26055.3--
2026.02
69.34485.171.2-
2026.02
68.45241.2--
2026.02
68.45241.254.3-
2025.12
68.45241.2--
67.55627.248.9-
67.55447.456.8-
2025.12
67.55627.2--
2025.12
67.55447.4--
2025.12
67.345.428.3--
2026.02
64.94638.550.7-
2026.01
64.96837.7--
2025.12
64.94638.5--
2026.01
646022.9-15.8
2026.02
63.64830.9--
2026.01
63.27034.2-3.4
2026.01
62.55533.3-13.9
2026.02
62.35648.255.4-
2026.01
62.35230.7-1.5
2026.02
61.4561441-
2025.12
61.45614--
2026.02
60.65476.666-
2026.02
60.54230.745-
2025.12
60.54235.3--
2026.02
59.74831.646.1-
2026.02
59.75631.647.5-
2026.02
59.7466760.2-
2026.02
59.54827.2--
2026.02
58.85826.345.3-
2026.02
58.84445.450.6-
2025.12
58.85826.3--
2026.02
573845.6--
2026.02
573845.648.9-
2026.02
574255.353.6-
2025.12
573845.6--
2026.02
56.15228.744.1-
2026.02
55.35216.7--
2026.02
55.34811.436-
2026.02
55.35216.738.9-
2025.12
55.35216.7--
2026.01
54.258.528.1-12.7
2026.02
52.63472.657.5-
2026.01
51.84833.3-6.2
2026.02
51.34261.153.6-
2026.02
50.937.527.2--
2026.02
49.14235.742.3-
2026.02
483026.936.1-
2026.02
47.44023.936.4-
2026.02
46.53623.735.3-
2026.02
434026.335.6-
2026.02
41.230.523.532-
2026.02
38.71821.227.8-
2026.02
38.430.521.5--
2026.02
36.82429.831.6-
2026.01
34.24420.2-11.3
2026.01
22.83619.3--
2026.01
21.93419.3-1.1
2026.01
20.23018.4-3.7
2026.01
14.12224.6-3.7
2026.02
12.32420.217.6-
2026.02
11.43621.219.8-
2026.01
73618.4-27