List your company

Multi-table Reasoning on MMQA 3-table

40.88AccuracyCPO
18.093624.009329.92535.8407Jun 3, 2026

Evaluation results

MethodLinks
CPOModel=Qwen3-14B2026.0640.88
CPOModel=Llama-3.1-8B2026.0635.19
CPOModel=Mistral-8B2026.0634.32
Trace SFTModel=Llama-3.1-8B2026.0628.84
Q&A SFTModel=Qwen3-14B2026.0628.53
Trace SFTModel=Qwen3-14B2026.0627
Trace SFTModel=Mistral-8B2026.0624.85
Q&A SFTModel=Mistral-8B2026.0621.47
Q&A SFTModel=Llama-3.1-8B2026.0618.97