# Multimodal Tool-Use on MMSearch-Plus Source: [Multimodal Tool-Use on MMSearch-Plus]() Collection index: [llms.txt]() Data updated: 2026-05-12T10:11:07.548Z Evaluation of model performance on the MMSearch-Plus dataset for Multimodal Tool-Use tasks, typically measured by Avg@4 and Pass@4. 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 Tool-Use | | Dataset (including any stated split) | MMSearch-Plus | | Metric | Avg@4 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [Avg@4](): Higher is better; unit: PERCENT. - [Pass@4](): Higher is better; unit: PERCENT. ## Recorded results | Method | Avg@4 | Result date | Report paper | | --- | --- | --- | --- | | Kimi-K2.5 | 33.53 | Not recorded | 6a02b408dbc836b87d824620 | | Qwen3.5-35B-A3B | 28.55 | Not recorded | 6a02b408dbc836b87d824620 | | Qwen3.5-Plus | 27.84 | Not recorded | 6a02b408dbc836b87d824620 | | Qwen3.5-35B-A3B | 23.93 | Not recorded | 6a02b408dbc836b87d824620 | | Gemini-2.5-Pro | 21.56 | Not recorded | 6a02b408dbc836b87d824620 | | GLM-4.6V | 17.42 | Not recorded | 6a02b408dbc836b87d824620 | | Qwen3.5-35B-A3B | 16.59 | Not recorded | 6a02b408dbc836b87d824620 | | o4-mini | 15.88 | Not recorded | 6a02b408dbc836b87d824620 | | GPT-5-mini | 14.22 | Not recorded | 6a02b408dbc836b87d824620 | | Kimi-K2.5 | 10.78 | Not recorded | 6a02b408dbc836b87d824620 | | Gemini-2.5-Pro | 10.43 | Not recorded | 6a02b408dbc836b87d824620 | | Qwen3.5-Plus | 6.64 | Not recorded | 6a02b408dbc836b87d824620 | | o4-mini | 5.92 | Not recorded | 6a02b408dbc836b87d824620 | | GLM-4.6V | 3.67 | Not recorded | 6a02b408dbc836b87d824620 | | Qwen3.5-35B-A3B | 3.67 | Not recorded | 6a02b408dbc836b87d824620 | | GPT-5-mini | 3.08 | Not recorded | 6a02b408dbc836b87d824620 | ### Kimi-K2.5 Avg@4: 33.53. Result ID: 6a02fc1347f34ce924e64ba6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Vanilla Tools"}. This record does not assert independent reproduction. ### Qwen3.5-35B-A3B Avg@4: 28.55. Result ID: 6a02fc1347f34ce924e64baa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"w/ ACE-SKILL"}. This record does not assert independent reproduction. ### Qwen3.5-Plus Avg@4: 27.84. Result ID: 6a02fc1347f34ce924e64ba2. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Vanilla Tools"}. This record does not assert independent reproduction. ### Qwen3.5-35B-A3B Avg@4: 23.93. Result ID: 6a02fc1347f34ce924e64ba9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"w/ XSkill"}. This record does not assert independent reproduction. ### Gemini-2.5-Pro Avg@4: 21.56. Result ID: 6a02fc1347f34ce924e64ba0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Vanilla Tools"}. This record does not assert independent reproduction. ### GLM-4.6V Avg@4: 17.42. Result ID: 6a02fc1347f34ce924e64ba4. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Vanilla Tools"}. This record does not assert independent reproduction. ### Qwen3.5-35B-A3B Avg@4: 16.59. Result ID: 6a02fc1347f34ce924e64ba8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Vanilla Tools"}. This record does not assert independent reproduction. ### o4-mini Avg@4: 15.88. Result ID: 6a02fc1347f34ce924e64b9c. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Vanilla Tools"}. This record does not assert independent reproduction. ### GPT-5-mini Avg@4: 14.22. Result ID: 6a02fc1347f34ce924e64b9e. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Vanilla Tools"}. This record does not assert independent reproduction. ### Kimi-K2.5 Avg@4: 10.78. Result ID: 6a02fc1347f34ce924e64ba5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Native Direct Answer"}. This record does not assert independent reproduction. ### Gemini-2.5-Pro Avg@4: 10.43. Result ID: 6a02fc1347f34ce924e64b9f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Native Direct Answer"}. This record does not assert independent reproduction. ### Qwen3.5-Plus Avg@4: 6.64. Result ID: 6a02fc1347f34ce924e64ba1. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Native Direct Answer"}. This record does not assert independent reproduction. ### o4-mini Avg@4: 5.92. Result ID: 6a02fc1347f34ce924e64b9b. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Native Direct Answer"}. This record does not assert independent reproduction. ### GLM-4.6V Avg@4: 3.67. Result ID: 6a02fc1347f34ce924e64ba3. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Native Direct Answer"}. This record does not assert independent reproduction. ### Qwen3.5-35B-A3B Avg@4: 3.67. Result ID: 6a02fc1347f34ce924e64ba7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Native Direct Answer"}. This record does not assert independent reproduction. ### GPT-5-mini Avg@4: 3.08. Result ID: 6a02fc1347f34ce924e64b9d. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Native Direct Answer"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.