List your company

Outcome Reasoning on RNN-Topo

88.9M' F1 MeanGPT-5
64.25270.65177.0583.449May 17, 2025

Evaluation results

MethodLinks
GPT-5Model=GPT-52025.0588.983.4
GPT-o4Model=GPT-o42025.0587.981.6
Llama4-MModel=Llama4-M2025.0580.575
DeepSeekModel=DeepSeek2025.0578.372
Gemini2.5Model=Gemini2.52025.0577.170.6
Qwen3Model=Qwen32025.0575.669.4
Llama4-SModel=Llama4-S2025.0565.258.7