# Multimodal Deep Search on MMSrch-Plus Source: [Multimodal Deep Search on MMSrch-Plus]() Collection index: [llms.txt]() Data updated: 2026-04-09T23:17:58.277Z Evaluation of model performance on the MMSrch-Plus dataset for Multimodal Deep Search tasks, 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 | Multimodal Deep Search | | Dataset (including any stated split) | MMSrch-Plus | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 | | --- | --- | --- | --- | | Gemini-3 Pro | 33.51 | Not recorded | 69d732707d0172140ec76a0c | | MTA-DeepSearch-32B | 31.93 | Not recorded | 69d732707d0172140ec76a0c | | GPT-5 | 31.61 | Not recorded | 69d732707d0172140ec76a0c | | Gemini-2.5 Pro | 30.65 | Not recorded | 69d732707d0172140ec76a0c | | MTA-DeepSearch-8B | 26.77 | Not recorded | 69d732707d0172140ec76a0c | | Gemini-3-pro | 26.37 | Not recorded | 69d732707d0172140ec76a0c | | Qwen3-VL-8B-Inst. | 18.38 | Not recorded | 69d732707d0172140ec76a0c | | Qwen3-VL-32B-Inst. | 14.84 | Not recorded | 69d732707d0172140ec76a0c | | GPT-5 | 13.18 | Not recorded | 69d732707d0172140ec76a0c | | Gemini-2.5-pro | 12.22 | Not recorded | 69d732707d0172140ec76a0c | | Qwen3-VL-32B-Inst. | 2.25 | Not recorded | 69d732707d0172140ec76a0c | | Qwen3-VL-8B-Inst. | 1.29 | Not recorded | 69d732707d0172140ec76a0c | ### Gemini-3 Pro Accuracy: 33.51. Result ID: 69d8334c47f34ce924bfdec9. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Agent Workflow"}. This record does not assert independent reproduction. ### MTA-DeepSearch-32B Accuracy: 31.93. Result ID: 69d8334c47f34ce924bfdecd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Ours","Model Scale":"32B"}. This record does not assert independent reproduction. ### GPT-5 Accuracy: 31.61. Result ID: 69d8334c47f34ce924bfdec7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Agent Workflow"}. This record does not assert independent reproduction. ### Gemini-2.5 Pro Accuracy: 30.65. Result ID: 69d8334c47f34ce924bfdec8. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Agent Workflow"}. This record does not assert independent reproduction. ### MTA-DeepSearch-8B Accuracy: 26.77. Result ID: 69d8334c47f34ce924bfdecc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Ours","Model Scale":"8B"}. This record does not assert independent reproduction. ### Gemini-3-pro Accuracy: 26.37. Result ID: 69d8334c47f34ce924bfdec4. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Direct Answer"}. This record does not assert independent reproduction. ### Qwen3-VL-8B-Inst. Accuracy: 18.38. Result ID: 69d8334c47f34ce924bfdeca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Agent Workflow","Model Scale":"8B"}. This record does not assert independent reproduction. ### Qwen3-VL-32B-Inst. Accuracy: 14.84. Result ID: 69d8334c47f34ce924bfdecb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Agent Workflow","Model Scale":"32B"}. This record does not assert independent reproduction. ### GPT-5 Accuracy: 13.18. Result ID: 69d8334c47f34ce924bfdec2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Direct Answer"}. This record does not assert independent reproduction. ### Gemini-2.5-pro Accuracy: 12.22. Result ID: 69d8334c47f34ce924bfdec3. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Direct Answer"}. This record does not assert independent reproduction. ### Qwen3-VL-32B-Inst. Accuracy: 2.25. Result ID: 69d8334c47f34ce924bfdec6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Direct Answer","Model Scale":"32B"}. This record does not assert independent reproduction. ### Qwen3-VL-8B-Inst. Accuracy: 1.29. Result ID: 69d8334c47f34ce924bfdec5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Direct Answer","Model Scale":"8B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.