List your company

Question Answering on 2WikiMultiHopQA (held-out)

77.4F1 ScoreRASER-3
28.83241.44154.0566.659Jun 1, 2026

Evaluation results

MethodLinks
RASER-3Reader=GPT-OSS-120B, N=5002026.0677.41.6
RASER-2Reader=GPT-OSS-120B, N=5002026.0676.31.3
ONE-SHOT RAGReader=GPT-OSS-120B, N=5002026.0675.41.1
RASER-3Reader=Gemma-3-31B, N=3002026.06701.6
RASER-2Reader=Gemma-3-31B, N=3002026.0665.61.2
ONE-SHOT RAGReader=Gemma-3-31B, N=3002026.0663962
RASER-3Reader=Llama-3.1-8B, N=3002026.0648.72.2
RASER-2Reader=Mistral-S-119B, N=3002026.0648.51.5
RASER-3Reader=Phi-4-mini, N=3002026.0647.42.3
RASER-3Reader=Llama-3-8B, N=3002026.0647.22.1
RASER-3Reader=Mistral-S-119B, N=3002026.0645.1979
ONE-SHOT RAGReader=Mistral-S-119B, N=3002026.0645970
RASER-2Reader=Phi-4-mini, N=3002026.0640.21.1
ONE-SHOT RAGReader=Phi-4-mini, N=3002026.0639.1904
RASER-2Reader=Llama-3-8B, N=3002026.06381.2
ONE-SHOT RAGReader=Llama-3-8B, N=3002026.0636.7932
RASER-2Reader=Llama-3.1-8B, N=3002026.0635.51.4
ONE-SHOT RAGReader=Llama-3.1-8B, N=3002026.0630.7954