List your company

Multiple Choice Question Answering on CommonsenseQA (CQA)

85.09AccuracyQwen3 30B
69.084473.239777.39581.5503Feb 18, 2026

Evaluation results

MethodLinks
Qwen3 30Bconfidence_type=normalized, evaluation_protocol=output probabilities2026.0285.0984.712.4
GLM4 9Bconfidence_type=normalized, evaluation_protocol=output probabilities2026.0281.8283.32.5
Gemma3 12Bconfidence_type=normalized, evaluation_protocol=output probabilities2026.0278.718220
Qwen3 4Bconfidence_type=normalized, evaluation_protocol=output probabilities2026.0278.2180.319.6
Gemma3 4Bconfidence_type=normalized, evaluation_protocol=output probabilities2026.0269.775.629.5