List your company

Question Answering on TriviaQA (Accg, Accv, AUROC, APGR)

64AccgMistral-7B† / Qwen-7B
40.0846.2952.558.71Mar 26, 2026

Evaluation results

MethodLinks
Mistral-7B† / Qwen-7BGenerator=Mistral-7B†, Verifier=Qwen-7B2026.036465184.8304276.62.222-1.068-0.5629.3
Llama-1B / Qwen-7BGenerator=Llama-1B, Verifier=Qwen-7B2026.0354651080.581.169.178.80.6960.7240.76457.4
Llama-3-8B / Mistral-7BGenerator=Llama-3-8B, Verifier=Mistral-7B2026.0343642085.888.783.392.30.8180.8380.85878.5
Llama-3-8B† / Qwen-7BGenerator=Llama-3-8B†, Verifier=Qwen-7B2026.0343652185.888.777.787.50.7890.8120.80675.5
Qwen-0.5B / Qwen-7BGenerator=Qwen-0.5B, Verifier=Qwen-7B2026.0341652477.372.681.882.40.6190.5980.73760.6