List your company

Tool Use on Tool Use (accuracy)

0.792AccuracyDRIFT
0.566320.624910.68350.74209Jun 29, 2026

Evaluation results

MethodLinks
DRIFTBase Model=Qwen3-8B, Evaluation Protocol=mean@162026.060.792
SRPOBase Model=Qwen3-8B, Evaluation Protocol=mean@16, Source=Cited from prior work2026.060.712
SDPOBase Model=Qwen3-8B, Evaluation Protocol=mean@16, Source=Cited from prior work2026.060.685
SDPOBase Model=Qwen3-8B, Evaluation Protocol=mean@16, Source=Reproduced2026.060.677
GRPOBase Model=Qwen3-8B, Evaluation Protocol=mean@16, Source=Reproduced2026.060.677
SC-SDPOBase Model=Qwen3-8B, Evaluation Protocol=mean@16, Source=Cited from prior work2026.060.673
GRPOBase Model=Qwen3-8B, Evaluation Protocol=mean@16, Source=Cited from prior work2026.060.657
Qwen3-8BBase Model=Qwen3-8B, Evaluation Protocol=mean@162026.060.575