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

Tool-use Agent Performance on τ²-bench

72.4ASR

MemMorph

4.59222.19639.857.404May 24, 2026
Updated 7d ago

Evaluation Results

MethodLinks
2026.05
72.4--------
2026.05
68.2--------
2026.05
64.7--------
2026.05
60.5--------
2026.05
57.5--------
2026.05
56.1--------
2026.05
55.9--------
2026.05
53.8--------
2026.05
52.8--------
2026.05
52.5--------
2026.05
51.5--------
2026.05
51.2--------
2026.05
50.5--------
2026.05
46.3--------
2026.05
45.5--------
2026.05
45.5--------
2026.05
40.8--------
2026.05
38.6--------
2026.05
38.1--------
2026.05
35.8--------
2026.05
32.9--------
2026.05
32--------
2026.05
31.5--------
2026.05
30.6--------
2026.05
29.9--------
2026.05
28.7--------
2026.05
27.9--------
2026.05
27.9--------
2026.05
26.7--------
2026.05
25.7--------
2026.05
24.8--------
2026.05
24.3--------
2026.05
23.4--------
2026.05
21.8--------
2026.05
21--------
2026.05
20.9--------
2026.05
19.3--------
2026.05
18.6--------
2026.05
18.6--------
2026.05
18.1--------
2026.05
16.7--------
2026.05
16.3--------
2026.05
16.1--------
2026.05
15--------
2026.05
14.5--------
2026.05
12.8--------
2026.05
12.3--------
2026.05
11.2--------
2026.05
10.9--------
2026.05
7.2--------
2026.01
-39.522.213.255.3743.84---
2026.01
-34.822.218.442.1757.5---
2026.01
-34.521.616.754.5645.66---
2026.01
-31.916.49.747.9252.05---
2026.01
-32.221.114.949.0751.12---
2026.01
-39.525.219.363.4336.65---
2026.01
-46.233.927.263.2936.92---
2026.01
-50.635.927.863.5736.59---
2026.01
-53.543.337.765.434.65---
2026.01
-52.342.436.866.2933.92---
2026.01
-45.336.633.360.6739.62---
2026.01
-56.446.842.169.3630.75---
2026.04
------53.7538.7536.25
2026.04
------53.1238.7538.12
2026.04
------554038.12
2026.04
------57.541.2540.62
2026.04
------56.2542.539.38
2026.04
------58.1243.7541.25
2026.04
------66.8747.543.75
2026.04
------75.6251.2578.12
2026.04
------76.2552.576.87
2026.04
------76.2553.7577.5
2026.04
------76.2553.7577.5
2026.04
------77.555.578.75
2026.04
------77.556.2579.37
2026.04
------78.1258.7582.5
2026.04
------76.257070.63
2026.04
------76.887068.75
2026.04
------77.571.2570.63
2026.04
------77.572.571.25
2026.04
------82.576.2571.88