List your company

Question Answering on SQA

79.62AccuracyExGRPO
53.131260.008166.88573.7619Feb 26, 2026

Evaluation results

MethodLinks
ExGRPOModel=Qwen2.5-7B-Instruct, Model Role=Student Model, Adapter=On-Policy Adapt.2026.0279.62
ExGRPOModel=Qwen2.5-7B-Instruct, Model Role=Student Model2026.0279.04
Zero-shotModel=Gemini-1.5-Pro, Model Role=Teacher Model2026.0278.6
Zero-shot-EIModel=Gemini-1.5-Pro, Model Role=Teacher Model2026.0278.55
On-Policy DistillationModel=Qwen2.5-7B-Instruct, Model Role=Student Model2026.0278.12
Divide-or-ConquerModel=Qwen2.5-7B-Instruct, Model Role=Student Model2026.0277.15
RevThinkModel=Qwen2.5-7B-Instruct, Model Role=Student Model2026.0277.02
Answer AugModel=Qwen2.5-7B-Instruct, Model Role=Student Model2026.0276.2
Question AugModel=Qwen2.5-7B-Instruct, Model Role=Student Model2026.0275.7
Rephrase QuestionModel=Qwen2.5-7B-Instruct, Model Role=Student Model2026.0275.26
Distill Step-by-StepModel=Qwen2.5-7B-Instruct, Model Role=Student Model2026.0274.12
SKDModel=Qwen2.5-7B-Instruct, Model Role=Student Model2026.0273.51
Zero-shotModel=Qwen2.5-7B-Instruct, Model Role=Student Model2026.0272.93
ExGRPOModel=Gemma-7B-it, Model Role=Student Model, Adapter=On-Policy Adapt.2026.0270.65
ExGRPOModel=Gemma-7B-it, Model Role=Student Model2026.0269.43
On-Policy DistillationModel=Gemma-7B-it, Model Role=Student Model2026.0266.23
RevThinkModel=Gemma-7B-it, Model Role=Student Model2026.0264.19
Divide-or-ConquerModel=Gemma-7B-it, Model Role=Student Model2026.0260.12
Answer AugModel=Gemma-7B-it, Model Role=Student Model2026.0257.21
SKDModel=Gemma-7B-it, Model Role=Student Model2026.0256.77
Distill Step-by-StepModel=Gemma-7B-it, Model Role=Student Model2026.0256.77
Zero-shotModel=Gemma-7B-it, Model Role=Student Model2026.0256.33
Question AugModel=Gemma-7B-it, Model Role=Student Model2026.0255.1
Rephrase QuestionModel=Gemma-7B-it, Model Role=Student Model2026.0254.15