# Agentic Search on Xbench DeepSearch 2505 Source: [Agentic Search on Xbench DeepSearch 2505]() Collection index: [llms.txt]() Data updated: 2026-04-21T12:16:17.779Z Evaluation of model performance on the Agentic Search task using the Xbench DeepSearch 2505 dataset, measured by Accuracy. 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 | Agentic Search | | Dataset (including any stated split) | Xbench DeepSearch 2505 | | Metric | Accuracy | | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | LiteResearcher-4B | 78 | Not recorded | 69e704d47d0172140ec7efe0 | | OpenAI-GPT-5-high | 77.8 | Not recorded | 69e704d47d0172140ec7efe0 | | Tongyi DeepResearch 30B | 75 | Not recorded | 69e704d47d0172140ec7efe0 | | Minimax-M2 | 72 | Not recorded | 69e704d47d0172140ec7efe0 | | DeepSeek-V3.2 | 71 | Not recorded | 69e704d47d0172140ec7efe0 | | DeepSeek-V3.1 | 71 | Not recorded | 69e704d47d0172140ec7efe0 | | GLM-4.6 | 70 | Not recorded | 69e704d47d0172140ec7efe0 | | AgentCPM-Explore-4B | 70 | Not recorded | 69e704d47d0172140ec7efe0 | | Kimi-Researcher | 69 | Not recorded | 69e704d47d0172140ec7efe0 | | Claude-4.5-Sonnet | 66 | Not recorded | 69e704d47d0172140ec7efe0 | | Claude-4-Sonnet | 64.6 | Not recorded | 69e704d47d0172140ec7efe0 | | DeepMiner-32B | 62 | Not recorded | 69e704d47d0172140ec7efe0 | | Kimi-K2-0905 | 61 | Not recorded | 69e704d47d0172140ec7efe0 | | Mirothinker 8B | 60.6 | Not recorded | 69e704d47d0172140ec7efe0 | | WebExplorer-8B | 53.7 | Not recorded | 69e704d47d0172140ec7efe0 | | WebSailor 30B | 53.3 | Not recorded | 69e704d47d0172140ec7efe0 | | ASearcher QWQ v2 | 51.1 | Not recorded | 69e704d47d0172140ec7efe0 | | WebDancer (QwQ) | 38.3 | Not recorded | 69e704d47d0172140ec7efe0 | ### LiteResearcher-4B Accuracy: 78. Result ID: 69e76a7847f34ce924cef339. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context Window":"128k","Memory Mechanism":"Disabled"}. This record does not assert independent reproduction. ### OpenAI-GPT-5-high Accuracy: 77.8. Result ID: 69e76a7847f34ce924cef32d. [Reporting paper]() Recorded evaluation configuration: {"Context Window":"128k","Memory Mechanism":"Disabled"}. This record does not assert independent reproduction. ### Tongyi DeepResearch 30B Accuracy: 75. Result ID: 69e76a7847f34ce924cef332. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context Window":"128k","Memory Mechanism":"Disabled"}. This record does not assert independent reproduction. ### Minimax-M2 Accuracy: 72. Result ID: 69e76a7847f34ce924cef32c. [Reporting paper]() Recorded evaluation configuration: {"Context Window":"128k","Memory Mechanism":"Disabled"}. This record does not assert independent reproduction. ### DeepSeek-V3.2 Accuracy: 71. Result ID: 69e76a7847f34ce924cef32a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context Window":"128k","Memory Mechanism":"Disabled"}. This record does not assert independent reproduction. ### DeepSeek-V3.1 Accuracy: 71. Result ID: 69e76a7847f34ce924cef32b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context Window":"128k","Memory Mechanism":"Disabled"}. This record does not assert independent reproduction. ### GLM-4.6 Accuracy: 70. Result ID: 69e76a7847f34ce924cef32e. [Reporting paper]() Recorded evaluation configuration: {"Context Window":"128k","Memory Mechanism":"Disabled"}. This record does not assert independent reproduction. ### AgentCPM-Explore-4B Accuracy: 70. Result ID: 69e76a7847f34ce924cef338. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context Window":"128k","Memory Mechanism":"Disabled"}. This record does not assert independent reproduction. ### Kimi-Researcher Accuracy: 69. Result ID: 69e76a7847f34ce924cef32f. [Reporting paper]() Recorded evaluation configuration: {"Context Window":"128k","Memory Mechanism":"Disabled"}. This record does not assert independent reproduction. ### Claude-4.5-Sonnet Accuracy: 66. Result ID: 69e76a7847f34ce924cef329. [Reporting paper]() Recorded evaluation configuration: {"Context Window":"128k","Memory Mechanism":"Disabled"}. This record does not assert independent reproduction. ### Claude-4-Sonnet Accuracy: 64.6. Result ID: 69e76a7847f34ce924cef328. [Reporting paper]() Recorded evaluation configuration: {"Context Window":"128k","Memory Mechanism":"Disabled"}. This record does not assert independent reproduction. ### DeepMiner-32B Accuracy: 62. Result ID: 69e76a7847f34ce924cef337. [Reporting paper]() Recorded evaluation configuration: {"Context Window":"128k","Memory Mechanism":"Disabled"}. This record does not assert independent reproduction. ### Kimi-K2-0905 Accuracy: 61. Result ID: 69e76a7847f34ce924cef330. [Reporting paper]() Recorded evaluation configuration: {"Context Window":"128k","Memory Mechanism":"Disabled"}. This record does not assert independent reproduction. ### Mirothinker 8B Accuracy: 60.6. Result ID: 69e76a7847f34ce924cef331. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Context Window":"128k","Memory Mechanism":"Disabled"}. This record does not assert independent reproduction. ### WebExplorer-8B Accuracy: 53.7. Result ID: 69e76a7847f34ce924cef336. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context Window":"128k","Memory Mechanism":"Disabled"}. This record does not assert independent reproduction. ### WebSailor 30B Accuracy: 53.3. Result ID: 69e76a7847f34ce924cef334. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context Window":"128k","Memory Mechanism":"Disabled"}. This record does not assert independent reproduction. ### ASearcher QWQ v2 Accuracy: 51.1. Result ID: 69e76a7847f34ce924cef333. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context Window":"128k","Memory Mechanism":"Disabled"}. This record does not assert independent reproduction. ### WebDancer (QwQ) Accuracy: 38.3. Result ID: 69e76a7847f34ce924cef335. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context Window":"128k","Memory Mechanism":"Disabled"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.