# Multihop Question Answering on MuSiQue (EM, ASR) Source: [Multihop Question Answering on MuSiQue (EM, ASR)]() Collection index: [llms.txt]() Data updated: 2026-07-02T08:40:29.028Z Evaluation of model performance on the MuSiQue dataset for Multihop Question Answering, reporting Exact Match (EM) and ASR metrics. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Multihop Question Answering | | Dataset (including any stated split) | MuSiQue | | Metric | EM | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 36 of 36 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [EM](): Higher is better; unit: PERCENT. - [ASR](): Higher is better; unit: PERCENT. ## Recorded results | Method | EM | Result date | Report paper | | --- | --- | --- | --- | | PARADOX | 42 | Not recorded | 6a45f087dc71372d7795a25c | | Clean (No Attack) | 38 | Not recorded | 6a45f087dc71372d7795a25c | | PARADOX | 34 | Not recorded | 6a45f087dc71372d7795a25c | | Clean (No Attack) | 32 | Not recorded | 6a45f087dc71372d7795a25c | | Naive | 31 | Not recorded | 6a45f087dc71372d7795a25c | | Topic | 30 | Not recorded | 6a45f087dc71372d7795a25c | | PoisonedRAG | 28 | Not recorded | 6a45f087dc71372d7795a25c | | PARADOX | 27 | Not recorded | 6a45f087dc71372d7795a25c | | Fake Completion | 26 | Not recorded | 6a45f087dc71372d7795a25c | | Naive | 26 | Not recorded | 6a45f087dc71372d7795a25c | | Ignore | 25 | Not recorded | 6a45f087dc71372d7795a25c | | PARADOX | 24 | Not recorded | 6a45f087dc71372d7795a25c | | Clean (No Attack) | 23 | Not recorded | 6a45f087dc71372d7795a25c | | Ignore | 21 | Not recorded | 6a45f087dc71372d7795a25c | | Naive | 20 | Not recorded | 6a45f087dc71372d7795a25c | | Fake Completion | 20 | Not recorded | 6a45f087dc71372d7795a25c | | Combined | 19 | Not recorded | 6a45f087dc71372d7795a25c | | Ignore | 19 | Not recorded | 6a45f087dc71372d7795a25c | | Naive | 18 | Not recorded | 6a45f087dc71372d7795a25c | | PoisonedRAG | 18 | Not recorded | 6a45f087dc71372d7795a25c | | Fake Completion | 18 | Not recorded | 6a45f087dc71372d7795a25c | | Fake Completion | 17 | Not recorded | 6a45f087dc71372d7795a25c | | PoisonedRAG | 17 | Not recorded | 6a45f087dc71372d7795a25c | | Topic | 17 | Not recorded | 6a45f087dc71372d7795a25c | | Clean (No Attack) | 17 | Not recorded | 6a45f087dc71372d7795a25c | | Combined | 16 | Not recorded | 6a45f087dc71372d7795a25c | | Topic | 16 | Not recorded | 6a45f087dc71372d7795a25c | | PoisonedRAG | 16 | Not recorded | 6a45f087dc71372d7795a25c | | Ignore | 15 | Not recorded | 6a45f087dc71372d7795a25c | | Combined | 14 | Not recorded | 6a45f087dc71372d7795a25c | | Combined | 14 | Not recorded | 6a45f087dc71372d7795a25c | | Topic | 13 | Not recorded | 6a45f087dc71372d7795a25c | | KidnapRAG | 9 | Not recorded | 6a45f087dc71372d7795a25c | | KidnapRAG | 9 | Not recorded | 6a45f087dc71372d7795a25c | | KidnapRAG | 8 | Not recorded | 6a45f087dc71372d7795a25c | | KidnapRAG | 2 | Not recorded | 6a45f087dc71372d7795a25c | ### PARADOX EM: 42. Result ID: 6a4623fb60b88bb339854060. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Llama-3.3-70B-Inst"}. This record does not assert independent reproduction. ### Clean (No Attack) EM: 38. Result ID: 6a4623fb60b88bb339854059. [Reporting paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Llama-3.3-70B-Inst"}. This record does not assert independent reproduction. ### PARADOX EM: 34. Result ID: 6a4623fb60b88bb339854057. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Qwen2.5-32B-Inst"}. This record does not assert independent reproduction. ### Clean (No Attack) EM: 32. Result ID: 6a4623fb60b88bb339854050. [Reporting paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Qwen2.5-32B-Inst"}. This record does not assert independent reproduction. ### Naive EM: 31. Result ID: 6a4623fb60b88bb33985405a. [Reporting paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Llama-3.3-70B-Inst"}. This record does not assert independent reproduction. ### Topic EM: 30. Result ID: 6a4623fb60b88bb339854067. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### PoisonedRAG EM: 28. Result ID: 6a4623fb60b88bb33985405f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Llama-3.3-70B-Inst"}. This record does not assert independent reproduction. ### PARADOX EM: 27. Result ID: 6a4623fb60b88bb339854069. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### Fake Completion EM: 26. Result ID: 6a4623fb60b88bb33985405c. [Reporting paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Llama-3.3-70B-Inst"}. This record does not assert independent reproduction. ### Naive EM: 26. Result ID: 6a4623fb60b88bb33985406c. [Reporting paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"DeepSeek-32B"}. This record does not assert independent reproduction. ### Ignore EM: 25. Result ID: 6a4623fb60b88bb339854052. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Qwen2.5-32B-Inst"}. This record does not assert independent reproduction. ### PARADOX EM: 24. Result ID: 6a4623fb60b88bb339854072. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"DeepSeek-32B"}. This record does not assert independent reproduction. ### Clean (No Attack) EM: 23. Result ID: 6a4623fb60b88bb339854062. [Reporting paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### Ignore EM: 21. Result ID: 6a4623fb60b88bb33985405b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Llama-3.3-70B-Inst"}. This record does not assert independent reproduction. ### Naive EM: 20. Result ID: 6a4623fb60b88bb339854051. [Reporting paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Qwen2.5-32B-Inst"}. This record does not assert independent reproduction. ### Fake Completion EM: 20. Result ID: 6a4623fb60b88bb339854065. [Reporting paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### Combined EM: 19. Result ID: 6a4623fb60b88bb339854066. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### Ignore EM: 19. Result ID: 6a4623fb60b88bb33985406d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"DeepSeek-32B"}. This record does not assert independent reproduction. ### Naive EM: 18. Result ID: 6a4623fb60b88bb339854063. [Reporting paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### PoisonedRAG EM: 18. Result ID: 6a4623fb60b88bb339854068. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### Fake Completion EM: 18. Result ID: 6a4623fb60b88bb33985406e. [Reporting paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"DeepSeek-32B"}. This record does not assert independent reproduction. ### Fake Completion EM: 17. Result ID: 6a4623fb60b88bb339854053. [Reporting paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Qwen2.5-32B-Inst"}. This record does not assert independent reproduction. ### PoisonedRAG EM: 17. Result ID: 6a4623fb60b88bb339854056. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Qwen2.5-32B-Inst"}. This record does not assert independent reproduction. ### Topic EM: 17. Result ID: 6a4623fb60b88bb33985405e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Llama-3.3-70B-Inst"}. This record does not assert independent reproduction. ### Clean (No Attack) EM: 17. Result ID: 6a4623fb60b88bb33985406b. [Reporting paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"DeepSeek-32B"}. This record does not assert independent reproduction. ### Combined EM: 16. Result ID: 6a4623fb60b88bb33985406f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"DeepSeek-32B"}. This record does not assert independent reproduction. ### Topic EM: 16. Result ID: 6a4623fb60b88bb339854070. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"DeepSeek-32B"}. This record does not assert independent reproduction. ### PoisonedRAG EM: 16. Result ID: 6a4623fb60b88bb339854071. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"DeepSeek-32B"}. This record does not assert independent reproduction. ### Ignore EM: 15. Result ID: 6a4623fb60b88bb339854064. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### Combined EM: 14. Result ID: 6a4623fb60b88bb339854054. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Qwen2.5-32B-Inst"}. This record does not assert independent reproduction. ### Combined EM: 14. Result ID: 6a4623fb60b88bb33985405d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Llama-3.3-70B-Inst"}. This record does not assert independent reproduction. ### Topic EM: 13. Result ID: 6a4623fb60b88bb339854055. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Qwen2.5-32B-Inst"}. This record does not assert independent reproduction. ### KidnapRAG EM: 9. Result ID: 6a4623fb60b88bb33985406a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### KidnapRAG EM: 9. Result ID: 6a4623fb60b88bb339854073. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"DeepSeek-32B"}. This record does not assert independent reproduction. ### KidnapRAG EM: 8. Result ID: 6a4623fb60b88bb339854058. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Qwen2.5-32B-Inst"}. This record does not assert independent reproduction. ### KidnapRAG EM: 2. Result ID: 6a4623fb60b88bb339854061. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Llama-3.3-70B-Inst"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.