List your company

Tool Use on StableToolBench cost-augmented

76PRINTENT
15.78431.41747.0562.683Feb 12, 2026

Evaluation results

MethodLinks
INTENTbackbone=GPT 5 nano, constraint_type=Enforce2026.027692.686.110029.217.91.792.162.4
MCObackbone=GPT 5 nano, constraint_type=Enforce2026.0271.48782.310031.918.11.872.232.28
INTENTbackbone=GPT 4.1 mini, constraint_type=Enforce2026.0263.877.873.310024.919.11.231.761.7
MCObackbone=GPT 4.1 mini, constraint_type=Enforce2026.0258.971.872.510027.118.71.92.052.15
BTPbackbone=GPT 5 nano, constraint_type=Enforce2026.0257.770.373.210036.218.81.221.670.87
DFSDTbackbone=GPT 5 nano, constraint_type=Enforce2026.0257.269.771.910035.618.61.10.911.08
BATSbackbone=GPT 4.1 mini, constraint_type=Enforce2026.025364.668.110035.620.81.963.554.13
BATSbackbone=GPT 5 nano, constraint_type=Enforce2026.0252.864.371.710032.617.37.6710.15.76
Promptbackbone=GPT 5 nano, constraint_type=Soft2026.0248.559.16287.638.120.10.640.60.76
BTPbackbone=GPT 4.1 mini, constraint_type=Enforce2026.0246.456.85910032.519.41.010.760.84
DFSDTbackbone=GPT 4.1 mini, constraint_type=Enforce2026.0244.954.755.410035.220.20.970.991.14
Promptbackbone=GPT 4.1 mini, constraint_type=Soft2026.0230.937.741.467.243.424.20.650.550.56
Rawbackbone=GPT 4.1 mini, constraint_type=Soft2026.0219.123.337.534.5102.128.2111
Rawbackbone=GPT 5 nano, constraint_type=Soft2026.0218.122.144.724.7145.827.8111