# Tool-use Agent on GAIA Source: [Tool-use Agent on GAIA]() Collection index: [llms.txt]() Data updated: 2026-03-11T09:21:10.985Z Evaluation of Tool-use Agent performance on the GAIA dataset, reporting scores broken down by modality (text, multimodal, file interaction) and overall. 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 | Tool-use Agent | | Dataset (including any stated split) | GAIA | | Metric | Text Success Rate | | 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 - [Text Success Rate](): Higher is better; unit: PERCENT. - [Multimodal Success Rate](): Higher is better; unit: PERCENT. - [File Interaction Success Rate](): Higher is better; unit: PERCENT. - [Overall Success Rate](): Higher is better; unit: PERCENT. ## Recorded results | Method | Text Success Rate | Result date | Report paper | | --- | --- | --- | --- | | AutoAgent | 64.1 | Not recorded | 69b0f70f2d603e6de3e45d6d | | AutoAgent | 62.1 | Not recorded | 69b0f70f2d603e6de3e45d6d | | Direct Answer | 44.7 | Not recorded | 69b0f70f2d603e6de3e45d6d | | AutoAgent | 43.7 | Not recorded | 69b0f70f2d603e6de3e45d6d | | Direct Answer | 42.7 | Not recorded | 69b0f70f2d603e6de3e45d6d | | DeepAgent | 42.5 | Not recorded | 69b0f70f2d603e6de3e45d6d | | DeepAgent | 38.8 | Not recorded | 69b0f70f2d603e6de3e45d6d | | ReAct | 36.9 | Not recorded | 69b0f70f2d603e6de3e45d6d | | ReAct | 32 | Not recorded | 69b0f70f2d603e6de3e45d6d | | DeepAgent | 32 | Not recorded | 69b0f70f2d603e6de3e45d6d | | ReAct | 26.2 | Not recorded | 69b0f70f2d603e6de3e45d6d | | Direct Answer | 10.7 | Not recorded | 69b0f70f2d603e6de3e45d6d | ### AutoAgent Text Success Rate: 64.1. Result ID: 69b133fe6dbb7075b95be1ba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"gemini-3-pro"}. This record does not assert independent reproduction. ### AutoAgent Text Success Rate: 62.1. Result ID: 69b133fe6dbb7075b95be1b6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"gemini-3-pro-thinking"}. This record does not assert independent reproduction. ### Direct Answer Text Success Rate: 44.7. Result ID: 69b133fe6dbb7075b95be1b3. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"gemini-3-pro-thinking"}. This record does not assert independent reproduction. ### AutoAgent Text Success Rate: 43.7. Result ID: 69b133fe6dbb7075b95be1b2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"gpt-4o"}. This record does not assert independent reproduction. ### Direct Answer Text Success Rate: 42.7. Result ID: 69b133fe6dbb7075b95be1b7. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"gemini-3-pro"}. This record does not assert independent reproduction. ### DeepAgent Text Success Rate: 42.5. Result ID: 69b133fe6dbb7075b95be1b1. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"gpt-4o"}. This record does not assert independent reproduction. ### DeepAgent Text Success Rate: 38.8. Result ID: 69b133fe6dbb7075b95be1b9. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"gemini-3-pro"}. This record does not assert independent reproduction. ### ReAct Text Success Rate: 36.9. Result ID: 69b133fe6dbb7075b95be1b8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"gemini-3-pro"}. This record does not assert independent reproduction. ### ReAct Text Success Rate: 32. Result ID: 69b133fe6dbb7075b95be1b4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"gemini-3-pro-thinking"}. This record does not assert independent reproduction. ### DeepAgent Text Success Rate: 32. Result ID: 69b133fe6dbb7075b95be1b5. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"gemini-3-pro-thinking"}. This record does not assert independent reproduction. ### ReAct Text Success Rate: 26.2. Result ID: 69b133fe6dbb7075b95be1b0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"gpt-4o"}. This record does not assert independent reproduction. ### Direct Answer Text Success Rate: 10.7. Result ID: 69b133fe6dbb7075b95be1af. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"gpt-4o"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.