# Multi-hop Question Answering on MuSiQue (pass@1) Source: [Multi-hop Question Answering on MuSiQue (pass@1)]() Collection index: [llms.txt]() Data updated: 2026-05-20T08:23:56.609Z Evaluation of model performance on the MuSiQue dataset for Multi-hop Question Answering, specifically measured using the pass@1 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) | MuSiQue | | Metric | pass@1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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@1](): Higher is better; unit: PERCENT. ## Recorded results | Method | pass@1 | Result date | Report paper | | --- | --- | --- | --- | | Qwen2.5-32B-Instruct + SSP | 32 | Not recorded | 68fa7c6d1e209131cea8e038 | | R-Search-7B + SSP | 31.4 | Not recorded | 68fa7c6d1e209131cea8e038 | | Search-R1-7B + SSP | 30.6 | Not recorded | 68fa7c6d1e209131cea8e038 | | R-Search-7B | 29.8 | Not recorded | 68fa7c6d1e209131cea8e038 | | Search-R1-7B | 29.6 | Not recorded | 68fa7c6d1e209131cea8e038 | | Qwen3-8B + SSP | 28 | Not recorded | 68fa7c6d1e209131cea8e038 | | Qwen2.5-14B-Instruct + SSP | 28 | Not recorded | 68fa7c6d1e209131cea8e038 | | Qwen2.5-32B-Instruct | 27.4 | Not recorded | 68fa7c6d1e209131cea8e038 | | Qwen3-8B | 26.6 | Not recorded | 68fa7c6d1e209131cea8e038 | | Qwen2.5-14B-Instruct | 26.6 | Not recorded | 68fa7c6d1e209131cea8e038 | | Qwen2.5-7B-Base + SSP | 24 | Not recorded | 68fa7c6d1e209131cea8e038 | | Qwen2.5-7B-Instruct + SSP | 21.2 | Not recorded | 68fa7c6d1e209131cea8e038 | | ZeroSearch-7B + SSP | 19.6 | Not recorded | 68fa7c6d1e209131cea8e038 | | ZeroSearch-7B | 17.6 | Not recorded | 68fa7c6d1e209131cea8e038 | | Qwen2.5-7B-Instruct | 16.8 | Not recorded | 68fa7c6d1e209131cea8e038 | | LLaMA-3.1-8B + SSP | 16.2 | Not recorded | 68fa7c6d1e209131cea8e038 | | LLaMA-3.1-8B | 11.4 | Not recorded | 68fa7c6d1e209131cea8e038 | | Qwen2.5-7B-Base | 11 | Not recorded | 68fa7c6d1e209131cea8e038 | ### Qwen2.5-32B-Instruct + SSP pass@1: 32. Result ID: 6a0d6f3cfbc373592c0569e8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Paradigm":"Scaling to Larger Models","SSP Integration":"true"}. This record does not assert independent reproduction. ### R-Search-7B + SSP pass@1: 31.4. Result ID: 6a0d6f3cfbc373592c0569e4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Paradigm":"Continual Training on Search-Specialized Agents","SSP Integration":"true"}. This record does not assert independent reproduction. ### Search-R1-7B + SSP pass@1: 30.6. Result ID: 6a0d6f3cfbc373592c0569e2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Paradigm":"Continual Training on Search-Specialized Agents","SSP Integration":"true"}. This record does not assert independent reproduction. ### R-Search-7B pass@1: 29.8. Result ID: 6a0d6f3cfbc373592c0569e3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Paradigm":"Continual Training on Search-Specialized Agents","SSP Integration":"false"}. This record does not assert independent reproduction. ### Search-R1-7B pass@1: 29.6. Result ID: 6a0d6f3cfbc373592c0569e1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Paradigm":"Continual Training on Search-Specialized Agents","SSP Integration":"false"}. This record does not assert independent reproduction. ### Qwen3-8B + SSP pass@1: 28. Result ID: 6a0d6f3cfbc373592c0569de. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Paradigm":"Generalization Across Model Families","SSP Integration":"true"}. This record does not assert independent reproduction. ### Qwen2.5-14B-Instruct + SSP pass@1: 28. Result ID: 6a0d6f3cfbc373592c0569e6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Paradigm":"Scaling to Larger Models","SSP Integration":"true"}. This record does not assert independent reproduction. ### Qwen2.5-32B-Instruct pass@1: 27.4. Result ID: 6a0d6f3cfbc373592c0569e7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Paradigm":"Scaling to Larger Models","SSP Integration":"false"}. This record does not assert independent reproduction. ### Qwen3-8B pass@1: 26.6. Result ID: 6a0d6f3cfbc373592c0569dd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Paradigm":"Generalization Across Model Families","SSP Integration":"false"}. This record does not assert independent reproduction. ### Qwen2.5-14B-Instruct pass@1: 26.6. Result ID: 6a0d6f3cfbc373592c0569e5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Paradigm":"Scaling to Larger Models","SSP Integration":"false"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Base + SSP pass@1: 24. Result ID: 6a0d6f3cfbc373592c0569d8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Paradigm":"From-Scratch Training on Base and Instruct Models","SSP Integration":"true"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct + SSP pass@1: 21.2. Result ID: 6a0d6f3cfbc373592c0569da. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Paradigm":"From-Scratch Training on Base and Instruct Models","SSP Integration":"true"}. This record does not assert independent reproduction. ### ZeroSearch-7B + SSP pass@1: 19.6. Result ID: 6a0d6f3cfbc373592c0569e0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Paradigm":"Continual Training on Search-Specialized Agents","SSP Integration":"true"}. This record does not assert independent reproduction. ### ZeroSearch-7B pass@1: 17.6. Result ID: 6a0d6f3cfbc373592c0569df. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Paradigm":"Continual Training on Search-Specialized Agents","SSP Integration":"false"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct pass@1: 16.8. Result ID: 6a0d6f3cfbc373592c0569d9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Paradigm":"From-Scratch Training on Base and Instruct Models","SSP Integration":"false"}. This record does not assert independent reproduction. ### LLaMA-3.1-8B + SSP pass@1: 16.2. Result ID: 6a0d6f3cfbc373592c0569dc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Paradigm":"Generalization Across Model Families","SSP Integration":"true"}. This record does not assert independent reproduction. ### LLaMA-3.1-8B pass@1: 11.4. Result ID: 6a0d6f3cfbc373592c0569db. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Paradigm":"Generalization Across Model Families","SSP Integration":"false"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Base pass@1: 11. Result ID: 6a0d6f3cfbc373592c0569d7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Paradigm":"From-Scratch Training on Base and Instruct Models","SSP Integration":"false"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.