List your company

Citation and Evidence Recall on MuSiQue

80.2RkGPT-5.2
7.19226.14645.164.054Oct 23, 2025

Evaluation results

MethodLinks
GPT-5.2Reasoning condition=Reasoning2025.1080.268.687
GPT-5-MiniReasoning condition=Reasoning2025.1073.264.580.5
Oracle-DRAGReasoning condition=No Reasoning2025.1070.410070.4
GPT-OSS-120BReasoning condition=Reasoning2025.1066.263.874.2
Phi-4Reasoning condition=No Reasoning2025.1064.736.375.4
Qwen3-32BReasoning condition=Reasoning2025.1062.554.476.1
Mistr-S-3.2-24BReasoning condition=No Reasoning2025.1061.55070.1
Qwen3-14BReasoning condition=Reasoning2025.1057.851.369.7
Qwen3-8BReasoning condition=Reasoning2025.1054.950.468
GPT-OSS-20BReasoning condition=Reasoning2025.1051.148.363.3
Oracle-BM25Reasoning condition=No Reasoning2025.1048.710048.7
Llama-3.1-8BReasoning condition=No Reasoning2025.1044.736.454.3
Qwen3-4BReasoning condition=Reasoning2025.104434.763.2
Phi-4-MiniReasoning condition=No Reasoning2025.1041.221.853.5
Llama-3.3-70BReasoning condition=No Reasoning2025.1041.129.649.1
Llama-3.2-3BReasoning condition=No Reasoning2025.1039.124.746
Qwen3-1.7BReasoning condition=Reasoning2025.1031.829.740.9
Ministr-8BReasoning condition=No Reasoning2025.1031.326.744
Qwen3-0.6BReasoning condition=Reasoning2025.1030.51.150
Llama-3.2-1BReasoning condition=No Reasoning2025.101011.514.1