List your company

Multiple-choice question answering on TIMESERIESEXAM

78AccuracyMhybrid
38.58448.81759.0569.283Jun 15, 2026

Evaluation results

MethodLinks
MhybridModel=gpt-oss-120b2026.0678
McodeModel=gpt-oss-120b2026.0670.4
MhybridModel=qwen3-next-80b2026.0668.1
MdirectModel=gpt-oss-120b2026.0665.3
MdirectModel=qwen3-next-80b2026.0663.5
McodeModel=qwen3-next-80b2026.0656.4
random2026.0640.1