List your company

Question Answering on Dataset A v0.4 (test)

4,582Solved Countthree-model oracle
775.61,763.82,7523,740.2Jun 11, 2026

Evaluation results

MethodLinks
three-model oraclemodel_pool=qwen, ds4, kimi2026.064,58283.25
kimirouting_strategy=always2026.064,12975.02
ds4routing_strategy=always2026.064,05673.69
qwenrouting_strategy=always2026.063,47763.17
unsolvable (any model)model_pool=qwen, ds4, kimi2026.0692216.75