List your company

Question Answering on HotpotQA (F1)

69.5F1 ScoreOracle
45.26851.55957.8564.141Jan 23, 2026

Evaluation results

MethodLinks
OracleBackbone=Llama 3.3 70B, Context Length=500 words2026.0169.5
OracleBackbone=Llama 3.3 70B, Context Length=1500 words2026.0169.5
OracleBackbone=Qwen 2.5 72B, Context Length=1500 words2026.0168.7
OracleBackbone=Llama 3.3 70B, Context Length=1000 words2026.0168.6
OracleBackbone=Qwen 2.5 72B, Context Length=500 words2026.0167.7
OracleBackbone=Qwen 2.5 72B, Context Length=1000 words2026.0167.5
DF-RAG + ICBackbone=Qwen 2.5 72B, Context Length=1000 words2026.0162.1
DF-RAG + ICBackbone=Llama 3.3 70B, Context Length=1500 words2026.0161.8
DF-RAGBackbone=Qwen 2.5 72B, Context Length=1500 words2026.0161.8
DF-RAG + ICBackbone=Qwen 2.5 72B, Context Length=1500 words2026.0160.9
DF-RAGBackbone=Qwen 2.5 72B, Context Length=1000 words2026.0160.4
DF-RAGBackbone=Llama 3.3 70B, Context Length=1000 words2026.0160.3
DF-RAG + ICBackbone=Qwen 2.5 72B, Context Length=500 words2026.0160.1
RAG with gMMRBackbone=Qwen 2.5 72B, Context Length=1500 words2026.0160.1
DF-RAGBackbone=Llama 3.3 70B, Context Length=1500 words2026.0159.6
DF-RAGBackbone=Qwen 2.5 72B, Context Length=500 words2026.0158.5
DF-RAG + ICBackbone=Llama 3.3 70B, Context Length=1000 words2026.0158.4
DF-RAGBackbone=Llama 3.3 70B, Context Length=500 words2026.0158.1
RAG with gMMRBackbone=Llama 3.3 70B, Context Length=1500 words2026.0158.1
Vanilla RAGBackbone=Qwen 2.5 72B, Context Length=1500 words2026.0157.9
LongRAGBackbone=Qwen 2.5 72B, Context Length=independent2026.0157.7
LongRAGBackbone=Llama 3.3 70B, Context Length=independent2026.0157.4
DF-RAG + ICBackbone=Llama 3.3 70B, Context Length=500 words2026.0156.8
RAG with gMMRBackbone=Qwen 2.5 72B, Context Length=1000 words2026.0156.7
Vanilla RAGBackbone=Llama 3.3 70B, Context Length=1500 words2026.0156.1
Vanilla RAGBackbone=Llama 3.3 70B, Context Length=1000 words2026.0156
RAG with gMMRBackbone=Llama 3.3 70B, Context Length=1000 words2026.0156
Vanilla RAGBackbone=Qwen 2.5 72B, Context Length=1000 words2026.0155.9
RAG with gMMRBackbone=Qwen 2.5 72B, Context Length=500 words2026.0155
RAPTORBackbone=Llama 3.3 70B, Context Length=independent2026.0154.5
RAG with gMMRBackbone=Llama 3.3 70B, Context Length=500 words2026.0153.3
RAPTORBackbone=Qwen 2.5 72B, Context Length=independent2026.0153
Vanilla RAGBackbone=Qwen 2.5 72B, Context Length=500 words2026.0151.2
Vanilla RAGBackbone=Llama 3.3 70B, Context Length=500 words2026.0151.1
HippoRAGBackbone=Qwen 2.5 72B, Context Length=independent2026.0147
HippoRAGBackbone=Llama 3.3 70B, Context Length=independent2026.0146.2