List your company

Question Answering on HotpotQA (held-out)

81.2F1 ScoreRASER-3
60.465.871.276.6Jun 1, 2026

Evaluation results

MethodLinks
RASER-3Reader=Gemma-3-31B, N=2002026.0681.21.8
RASER-2Reader=Gemma-3-31B, N=2002026.0679.61.4
RASER-3Reader=GPT-OSS-120B, N=5002026.0678.71.8
ONE-SHOT RAGReader=Gemma-3-31B, N=2002026.0678.71.3
RASER-2Reader=GPT-OSS-120B, N=5002026.0677.91.5
ONE-SHOT RAGReader=GPT-OSS-120B, N=5002026.0677.71.4
RASER-3Reader=Mistral-S-119B, N=2002026.0672.32.2
RASER-2Reader=Mistral-S-119B, N=2002026.0670.21.4
ONE-SHOT RAGReader=Mistral-S-119B, N=2002026.0669.91.3
RASER-3Reader=Llama-3-8B, N=2002026.0665.52.2
RASER-3Reader=Llama-3.1-8B, N=2002026.0665.42.4
RASER-3Reader=Phi-4-mini, N=2002026.0665.22.2
RASER-2Reader=Llama-3-8B, N=2002026.0663.51.3
RASER-2Reader=Phi-4-mini, N=2002026.0663.51.4
ONE-SHOT RAGReader=Phi-4-mini, N=2002026.0663.41.2
ONE-SHOT RAGReader=Llama-3-8B, N=2002026.0663.21.2
RASER-2Reader=Llama-3.1-8B, N=2002026.0662.41.5
ONE-SHOT RAGReader=Llama-3.1-8B, N=2002026.0661.21.3