List your company

Simulation Performance on R2

46AccuracyCAPO-tol1
16.8824.443239.56May 27, 2026

Evaluation results

MethodLinks
CAPO-tol1Model=Llama3.2, Setting=CAPO-tol12026.05461.470.2930.8890.5820.18798.898.50.99553—
CAPOBackbone=Llama3.22026.05461.47———0.187—98.50.995530.293
CAPO-tol1Model=Qwen3, Setting=CAPO-tol12026.0545.51.490.3160.8920.5950.11297.196.40.97356—
CAPOBackbone=Qwen32026.0545.51.49———0.112—96.40.973560.316
SFT-ind.Model=Qwen3, Setting=SFT-ind.2026.05451.4780.3070.8910.5820.1393.692.90.93651.2—
SFT-ind.Model=Llama3.2, Setting=SFT-ind.2026.05451.5350.290.8890.570.11896.996.30.97251.2—
SFTBackbone=Qwen32026.05451.478———0.13—92.90.93651.20.307
SFTBackbone=Llama3.22026.05451.535———0.118—96.30.97251.20.29
SFT-sharedModel=Qwen3, Setting=SFT-shared2026.0544.31.6170.3040.890.5690.2280.7800.80645.5—
VP-ICLModel=Qwen3, Setting=VP-ICL2026.0541.51.6670.2760.8850.6010.24693.894.70.95651—
VP-ICLBackbone=Qwen32026.0541.51.667———0.246—94.70.956510.276
ICLModel=Qwen3, Setting=ICL2026.0540.71.7020.1970.8710.5350.5878080.90.8146.3—
ICLBackbone=Qwen32026.0540.71.702———0.587—80.90.8146.30.197
SFT-sharedModel=Llama3.2, Setting=SFT-shared2026.0538.52.050.2090.870.4250.68330.530.50.19126.5—
BaseModel=Qwen3, Setting=Base2026.0529.22.4530.0710.840.3955.18824.824.8-0.00423.7—
BaseBackbone=Qwen32026.0529.22.453———5.188—24.8-0.00423.70.071
VPModel=Qwen3, Setting=VP2026.0527.82.4750.10.850.482.7465.764.90.65136—
VPBackbone=Qwen32026.0527.82.475———2.74—64.90.651360.1
ICLModel=Llama3.2, Setting=ICL2026.0527.33.3330.2130.8750.5460.4887.587.10.87936.7—
VP-ICLModel=Llama3.2, Setting=VP-ICL2026.0527.33.390.230.880.5580.25787.585.80.86537—
ICLBackbone=Llama3.22026.0527.33.333———0.48—87.10.87936.70.213
VP-ICLBackbone=Llama3.22026.0527.33.39———0.257—85.80.865370.23
BaseModel=Llama3.2, Setting=Base2026.0520.73.1880.0680.8350.381.51525.125.50.01523—
BaseBackbone=Llama3.22026.0520.73.188———1.515—25.50.015230.068
VPModel=Llama3.2, Setting=VP2026.05184.1850.0980.850.4010.91334.735.90.17526—
VPBackbone=Llama3.22026.05184.185———0.913—35.90.175260.098