List your company

Biomedical Evidence Synthesis on COCHRANEFOREST (test)

67.3F1 ScoreURCA
22.37234.03645.757.364May 9, 2025

Evaluation results

MethodLinks
URCALLM=Mistral-Large (2407), 128B2025.0567.365.269.567
URCALLM=LlaMa 3.1, 70B2025.0566.16468.464.6
URCALLM=GPT-4 (0613)2025.0565.76368.764.1
GraphRAGLLM=LlaMa 3.1, 70B2025.0565.664.866.363.4
GraphRAGLLM=Mistral-Large (2407), 128B2025.0564.963.86666.3
GraphRAGLLM=GPT-4 (0613)2025.0563.861.666.163.7
RAG + Uniform RetrievalLLM=LlaMa 3.1, 70B2025.0563.461.565.564.2
RAG + Uniform RetrievalLLM=Mistral-Large (2407), 128B2025.0563.360.965.863.2
AbstractsLLM=Mistral-Large (2407), 128B2025.0562.660.36562.6
InstructRAGLLM=Mistral-Large (2407), 128B2025.0562.661.563.664.4
URCALLM=GPT-3.5-Turbo (0613)2025.0562.460.664.463.5
RAGLLM=LlaMa 3.1, 70B2025.0562.160.264.162.9
RAG + Uniform RetrievalLLM=GPT-4 (0613)2025.056259.764.561.8
RAG + Uniform RetrievalLLM=GPT-3.5-Turbo (0613)2025.0561.86063.862.8
RAPTORLLM=Mistral-Large (2407), 128B2025.0561.759.164.661
RAGLLM=GPT-4 (0613)2025.0561.659.36461.6
InstructRAGLLM=GPT-4 (0613)2025.0561.661.461.963.3
AbstractsLLM=GPT-4 (0613)2025.056160.261.962.6
RAGLLM=Mistral-Large (2407), 128B2025.0560.960.76164.3
InstructRAGLLM=LlaMa 3.1, 70B2025.0560.959.662.362.1
AbstractsLLM=LlaMa 3.1, 70B2025.0560.760.461.164.1
RAPTORLLM=LlaMa 3.1, 70B2025.0560.658.263.260
RAPTORLLM=GPT-4 (0613)2025.0560.158.26260.8
RAGLLM=GPT-3.5-Turbo (0613)2025.0559.157.660.660.7
InstructRAGLLM=GPT-3.5-Turbo (0613)2025.0557.457.157.761.1
GraphRAGLLM=GPT-3.5-Turbo (0613)2025.0556.658.454.959.3
AbstractsLLM=GPT-3.5-Turbo (0613)2025.055655.256.958.8
RAPTORLLM=GPT-3.5-Turbo (0613)2025.0553.65255.354.1
No RAGLLM=LlaMa 3.1, 70B2025.0549.146.152.445.2
No RAGLLM=GPT-4 (0613)2025.0547.555.941.259.5
No RAGLLM=Mistral-Large (2407), 128B2025.0546.147.444.853.1
No RAGLLM=GPT-3.5-Turbo (0613)2025.0524.118.933.256.4