# Multi-Hop Question Answering on 2Wiki (test) (Pass@3) Source: [Multi-Hop Question Answering on 2Wiki (test) (Pass@3)]() Collection index: [llms.txt]() Data updated: 2026-07-07T09:11:03.842Z Evaluation of model performance on the test split of the 2Wiki dataset for multi-hop question answering, specifically measured using the Pass@3 metric. 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 | Multi-Hop Question Answering | | Dataset (including any stated split) | 2Wiki (test) | | Metric | Pass@3 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 8 of 8 | | 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 - [Pass@3](): Higher is better; unit: PERCENT. ## Recorded results | Method | Pass@3 | Result date | Report paper | | --- | --- | --- | --- | | PivoARL | 64 | Not recorded | 6a4c880585dba69fef8b263d | | MetaRL | 55.2 | Not recorded | 6a4c880585dba69fef8b263d | | Search-R1 | 52.4 | Not recorded | 6a4c880585dba69fef8b263d | | StepSearch | 50 | Not recorded | 6a4c880585dba69fef8b263d | | GiGPO | 47.9 | Not recorded | 6a4c880585dba69fef8b263d | | ZeroSearch | 47.3 | Not recorded | 6a4c880585dba69fef8b263d | | GRPO | 46.4 | Not recorded | 6a4c880585dba69fef8b263d | | GSPO | 43 | Not recorded | 6a4c880585dba69fef8b263d | ### PivoARL Pass@3: 64. Result ID: 6a4cc28f60b88bb339c94728. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-4B","Search-augmented":"true","Domain":"Out-of-domain"}. This record does not assert independent reproduction. ### MetaRL Pass@3: 55.2. Result ID: 6a4cc28f60b88bb339c94727. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-4B","Search-augmented":"true","Domain":"Out-of-domain"}. This record does not assert independent reproduction. ### Search-R1 Pass@3: 52.4. Result ID: 6a4cc28f60b88bb339c94721. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-4B","Search-augmented":"true","Domain":"Out-of-domain"}. This record does not assert independent reproduction. ### StepSearch Pass@3: 50. Result ID: 6a4cc28f60b88bb339c94723. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-4B","Search-augmented":"true","Domain":"Out-of-domain"}. This record does not assert independent reproduction. ### GiGPO Pass@3: 47.9. Result ID: 6a4cc28f60b88bb339c94725. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-4B","Search-augmented":"true","Domain":"Out-of-domain"}. This record does not assert independent reproduction. ### ZeroSearch Pass@3: 47.3. Result ID: 6a4cc28f60b88bb339c94722. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-4B","Search-augmented":"true","Domain":"Out-of-domain"}. This record does not assert independent reproduction. ### GRPO Pass@3: 46.4. Result ID: 6a4cc28f60b88bb339c94724. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-4B","Search-augmented":"true","Domain":"Out-of-domain"}. This record does not assert independent reproduction. ### GSPO Pass@3: 43. Result ID: 6a4cc28f60b88bb339c94726. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-4B","Search-augmented":"true","Domain":"Out-of-domain"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.