List your company

Predict Move on Predict Move 400 samples

98Prediction Move Legal %SFT8 XL
4.428.75377.3Apr 6, 2026

Evaluation results

MethodLinks
SFT8 XLSFT Train Tokens=60M, RL Samples=16k, Stage=RL2026.04980.8212
SFT8 + SFT9 XLcSFT Train Tokens=120M, RL Samples=16k, Stage=RL2026.04980.8322
gpt-oss-120b (Medium)SFT Train Tokens=–, RL Samples=–, Stage=SFT2026.04940.662
SFT6 [BM]SFT Train Tokens=15M, RL Samples=8k, Stage=RL2026.04930.7131
SFT9 XLSFT Train Tokens=60M, RL Samples=16k, Stage=RL2026.04930.7525
SFT8 [BM - All]SFT Train Tokens=15M, RL Samples=8k, Stage=RL2026.04900.7114
SFT9 [BL - All]SFT Train Tokens=15M, RL Samples=8k, Stage=RL2026.04890.6432
SFT7 [BL]SFT Train Tokens=15M, RL Samples=8k, Stage=RL2026.04850.6364
SFT1 [RSPM]SFT Train Tokens=15M, RL Samples=8ka, Stage=RL2026.04820.5255
SFT2 [RSA]SFT Train Tokens=15M, RL Samples=8k, Stage=RL2026.04730.648
SFT4 [FBA]SFT Train Tokens=15M, RL Samples=8k, Stage=RL2026.04720.5440
SFT5 [GS]SFT Train Tokens=15M, RL Samples=8k, Stage=RL2026.04710.5442
SFT3 [VABP]SFT Train Tokens=15M, RL Samples=8k, Stage=RL2026.04670.5346
SFT8 [BM - All]SFT Train Tokens=15M, RL Samples=8k, Stage=SFT2026.04600.63
SFT8 XLSFT Train Tokens=60M, RL Samples=16k, Stage=SFT2026.04550.623
SFT8 + SFT9 XLcSFT Train Tokens=120M, RL Samples=16k, Stage=SFT2026.04540.582
SFT9 XLSFT Train Tokens=60M, RL Samples=16k, Stage=SFT2026.04520.63
SFT9 [BL - All]SFT Train Tokens=15M, RL Samples=8k, Stage=SFT2026.04510.67
SFT7 [BL]SFT Train Tokens=15M, RL Samples=8k, Stage=SFT2026.04480.622
SFT4 [FBA]SFT Train Tokens=15M, RL Samples=8k, Stage=SFT2026.04440.593
SFT6 [BM]SFT Train Tokens=15M, RL Samples=8k, Stage=SFT2026.04440.644
Llama 4 MaverickSFT Train Tokens=–, RL Samples=–, Stage=SFT2026.04420.621
SFT3 [VABP]SFT Train Tokens=15M, RL Samples=8k, Stage=SFT2026.04400.613
SFT2 [RSA]SFT Train Tokens=15M, RL Samples=8k, Stage=SFT2026.04370.635
SFT5 [GS]SFT Train Tokens=15M, RL Samples=8k, Stage=SFT2026.04360.63
SFT1 [RSPM]SFT Train Tokens=15M, RL Samples=8ka, Stage=SFT2026.04340.634
Qwen2.5 7B-InstructSFT Train Tokens=–, RL Samples=–, Stage=SFT2026.0480.566