List your company

Question Answering on MuSiQue (held-out)

57.7F1 ScoreIRCOT*
19.42829.36439.349.236Jun 1, 2026

Evaluation results

MethodLinks
IRCOT*Reader=Gemma-3-31B, N=3002026.0657.73,800
a-PRUNEReader=GPT-OSS-120B, N=5002026.0652.84,800
RASER-3Reader=GPT-OSS-120B, N=5002026.06512,200
a-PRUNEReader=Gemma-3-31B, N=3002026.0650.33,700
RASER-2Reader=GPT-OSS-120B, N=5002026.0650.22,100
RASER-3Reader=Gemma-3-31B, N=3002026.0650.22,400
IRCOT*Reader=Mistral-S-119B, N=3002026.0649.94,300
ONE-SHOT RAGReader=GPT-OSS-120B, N=5002026.0648.81,500
SELF-ASK*Reader=GPT-OSS-120B, N=5002026.0648.24,600
ChainRAG†Reader=GPT-OSS-120B, N=5002026.0646.54,600
ChainRAG†Reader=Mistral-S-119B, N=3002026.0646.42,300
RASER-2Reader=Gemma-3-31B, N=3002026.0645.82,100
IRCOT*Reader=GPT-OSS-120B, N=5002026.0645.54,300
ChainRAG†Reader=Gemma-3-31B, N=3002026.0644.52,300
RASER-3Reader=Mistral-S-119B, N=3002026.0640.82,400
SELF-ASK*Reader=Phi-4-mini, N=3002026.0640.73,000
a-PRUNEReader=Mistral-S-119B, N=3002026.0639.73,800
ONE-SHOT RAGReader=Gemma-3-31B, N=3002026.0639.31,200
SELF-ASK*Reader=Mistral-S-119B, N=3002026.06383,300
IRCOT*Reader=Llama-3.1-8B, N=3002026.0637.65,100
IRCOT*Reader=Phi-4-mini, N=3002026.0637.25,400
SELF-ASK*Reader=Gemma-3-31B, N=3002026.06363,000
RASER-3Reader=Phi-4-mini, N=3002026.0635.72,700
IRCOT*Reader=Llama-3-8B, N=3002026.0635.44,700
a-PRUNEReader=Phi-4-mini, N=3002026.0635.33,600
RASER-2Reader=Phi-4-mini, N=3002026.0633.51,400
ONE-SHOT RAGReader=Phi-4-mini, N=3002026.0633.11,100
RASER-3Reader=Llama-3.1-8B, N=3002026.06333,000
ChainRAG†Reader=Llama-3.1-8B, N=3002026.0631.22,600
RASER-3Reader=Llama-3-8B, N=3002026.0630.92,800
RASER-2Reader=Mistral-S-119B, N=3002026.0630.61,900
ChainRAG†Reader=Phi-4-mini, N=3002026.0629.31,900
SELF-ASK*Reader=Llama-3-8B, N=3002026.0629.23,200
ONE-SHOT RAGReader=Mistral-S-119B, N=3002026.0628.31,200
SELF-ASK*Reader=Llama-3.1-8B, N=3002026.0627.63,200
a-PRUNEReader=Llama-3.1-8B, N=3002026.0626.43,800
a-PRUNEReader=Llama-3-8B, N=3002026.0625.63,700
RASER-2Reader=Llama-3.1-8B, N=3002026.0625.31,500
ONE-SHOT RAGReader=Llama-3.1-8B, N=3002026.0623.61,200
RASER-2Reader=Llama-3-8B, N=3002026.0622.91,600
ONE-SHOT RAGReader=Llama-3-8B, N=3002026.0622.31,200
ChainRAG†Reader=Llama-3-8B, N=3002026.0620.92,800