List your company

Multiple Choice Question Answering on BGB (test)

78.8Exact AccuracyGPT-5 (min. reasoning)
63.40867.40471.475.396Jan 20, 2026

Evaluation results

MethodLinks
GPT-5 (min. reasoning)Train Data=Base Model2026.0178.8
GPT-5-mini (min. reasoning)Train Data=Base Model2026.0175.8
Gemma 3 (12B)Train Data=Difficulty-Graded QA Data2026.0175.1
LLaMA 3.1 (8B)Train Data=Difficulty-Graded QA Data2026.0168.2
Gemma 3 (12B)Train Data=Standard Instruction QA Data2026.0167.1
Gemma 3 (12B)Train Data=Base Model2026.0167
LLaMA 3.1 (8B)Train Data=Standard Instruction QA Data2026.0164.2
LLaMA 3.1 (8B)Train Data=Base Model2026.0164