# Long-horizon agentic task on DeepSearchQA Source: [Long-horizon agentic task on DeepSearchQA]() Collection index: [llms.txt]() Data updated: 2026-04-14T12:42:04.770Z Evaluation of model performance on the DeepSearchQA dataset for Long-horizon agentic tasks, reporting Performance. 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 | Long-horizon agentic task | | Dataset (including any stated split) | DeepSearchQA | | Metric | Performance | | 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 - [Performance](): Higher is better; unit: PERCENT. ## Recorded results | Method | Performance | Result date | Report paper | | --- | --- | --- | --- | | AggAgent | 66 | Not recorded | 69ddca827d0172140ec7a018 | | AggAgent | 65.33 | Not recorded | 69ddca827d0172140ec7a018 | | Summary Aggregation | 64 | Not recorded | 69ddca827d0172140ec7a018 | | Best-of-N | 64 | Not recorded | 69ddca827d0172140ec7a018 | | Solution Aggregation | 62.67 | Not recorded | 69ddca827d0172140ec7a018 | | Solution Aggregation | 62 | Not recorded | 69ddca827d0172140ec7a018 | | Summary Aggregation | 61.33 | Not recorded | 69ddca827d0172140ec7a018 | | Best-of-N | 57.33 | Not recorded | 69ddca827d0172140ec7a018 | | Fewest Tool Calls | 56 | Not recorded | 69ddca827d0172140ec7a018 | | Fewest Tool Calls | 54.67 | Not recorded | 69ddca827d0172140ec7a018 | | Pass@1 | 54.42 | Not recorded | 69ddca827d0172140ec7a018 | | AggAgent | 49.33 | Not recorded | 69ddca827d0172140ec7a018 | | Pass@1 | 49.25 | Not recorded | 69ddca827d0172140ec7a018 | | Summary Aggregation | 47.33 | Not recorded | 69ddca827d0172140ec7a018 | | Solution Aggregation | 46 | Not recorded | 69ddca827d0172140ec7a018 | | Best-of-N | 35.33 | Not recorded | 69ddca827d0172140ec7a018 | | Fewest Tool Calls | 33.33 | Not recorded | 69ddca827d0172140ec7a018 | | Pass@1 | 32.42 | Not recorded | 69ddca827d0172140ec7a018 | ### AggAgent Performance: 66. Result ID: 69de35e447f34ce924c71c06. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.5-122B","Aggregation Category":"LLM-based Aggregation","Number of Rollouts (K)":"8"}. This record does not assert independent reproduction. ### AggAgent Performance: 65.33. Result ID: 69de35e447f34ce924c71c0c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"MiniMax-M2.5","Aggregation Category":"LLM-based Aggregation","Number of Rollouts (K)":"8"}. This record does not assert independent reproduction. ### Summary Aggregation Performance: 64. Result ID: 69de35e447f34ce924c71c05. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.5-122B","Aggregation Category":"LLM-based Aggregation","Number of Rollouts (K)":"8"}. This record does not assert independent reproduction. ### Best-of-N Performance: 64. Result ID: 69de35e447f34ce924c71c08. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"MiniMax-M2.5","Aggregation Category":"Heuristic Aggregation","Number of Rollouts (K)":"8"}. This record does not assert independent reproduction. ### Solution Aggregation Performance: 62.67. Result ID: 69de35e447f34ce924c71c04. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.5-122B","Aggregation Category":"LLM-based Aggregation","Number of Rollouts (K)":"8"}. This record does not assert independent reproduction. ### Solution Aggregation Performance: 62. Result ID: 69de35e447f34ce924c71c0a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"MiniMax-M2.5","Aggregation Category":"LLM-based Aggregation","Number of Rollouts (K)":"8"}. This record does not assert independent reproduction. ### Summary Aggregation Performance: 61.33. Result ID: 69de35e447f34ce924c71c0b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"MiniMax-M2.5","Aggregation Category":"LLM-based Aggregation","Number of Rollouts (K)":"8"}. This record does not assert independent reproduction. ### Best-of-N Performance: 57.33. Result ID: 69de35e447f34ce924c71c02. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.5-122B","Aggregation Category":"Heuristic Aggregation","Number of Rollouts (K)":"8"}. This record does not assert independent reproduction. ### Fewest Tool Calls Performance: 56. Result ID: 69de35e447f34ce924c71c09. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"MiniMax-M2.5","Aggregation Category":"Heuristic Aggregation","Number of Rollouts (K)":"8"}. This record does not assert independent reproduction. ### Fewest Tool Calls Performance: 54.67. Result ID: 69de35e447f34ce924c71c03. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.5-122B","Aggregation Category":"Heuristic Aggregation","Number of Rollouts (K)":"8"}. This record does not assert independent reproduction. ### Pass@1 Performance: 54.42. Result ID: 69de35e447f34ce924c71c07. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"MiniMax-M2.5","Aggregation Category":"Single Rollout","Number of Rollouts (K)":"1"}. This record does not assert independent reproduction. ### AggAgent Performance: 49.33. Result ID: 69de35e447f34ce924c71c00. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GLM-4.7-Flash","Aggregation Category":"LLM-based Aggregation","Number of Rollouts (K)":"8"}. This record does not assert independent reproduction. ### Pass@1 Performance: 49.25. Result ID: 69de35e447f34ce924c71c01. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.5-122B","Aggregation Category":"Single Rollout","Number of Rollouts (K)":"1"}. This record does not assert independent reproduction. ### Summary Aggregation Performance: 47.33. Result ID: 69de35e447f34ce924c71bff. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GLM-4.7-Flash","Aggregation Category":"LLM-based Aggregation","Number of Rollouts (K)":"8"}. This record does not assert independent reproduction. ### Solution Aggregation Performance: 46. Result ID: 69de35e447f34ce924c71bfe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GLM-4.7-Flash","Aggregation Category":"LLM-based Aggregation","Number of Rollouts (K)":"8"}. This record does not assert independent reproduction. ### Best-of-N Performance: 35.33. Result ID: 69de35e447f34ce924c71bfc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GLM-4.7-Flash","Aggregation Category":"Heuristic Aggregation","Number of Rollouts (K)":"8"}. This record does not assert independent reproduction. ### Fewest Tool Calls Performance: 33.33. Result ID: 69de35e447f34ce924c71bfd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GLM-4.7-Flash","Aggregation Category":"Heuristic Aggregation","Number of Rollouts (K)":"8"}. This record does not assert independent reproduction. ### Pass@1 Performance: 32.42. Result ID: 69de35e447f34ce924c71bfb. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"GLM-4.7-Flash","Aggregation Category":"Single Rollout","Number of Rollouts (K)":"1"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.