# General Assistant Tasks on GAIA Source: [General Assistant Tasks on GAIA]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:05:10.050Z Evaluation of general assistant capabilities on the GAIA dataset, measured using Success Rate (%) and Best Delta (pp). 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 | General Assistant Tasks | | Dataset (including any stated split) | GAIA | | Metric | Success Rate | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 15 of 15 | | 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 - [Success Rate](): Higher is better; unit: PERCENT. - [Best Delta (pp)](): Lower is better; unit: SCALAR. ## Recorded results | Method | Success Rate | Result date | Report paper | | --- | --- | --- | --- | | MiniMax-M2.1 | 46.7 | Not recorded | 6982d2a6a8b01e76cc8e9500 | | GLM-4.7 | 34.4 | Not recorded | 6982d2a6a8b01e76cc8e9500 | | GLM-4.7 | 31.1 | Not recorded | 6982d2a6a8b01e76cc8e9500 | | GLM-4.7 | 27.8 | Not recorded | 6982d2a6a8b01e76cc8e9500 | | GLM-4.7 | 23.3 | Not recorded | 6982d2a6a8b01e76cc8e9500 | | GLM-4.7 | 23.3 | Not recorded | 6982d2a6a8b01e76cc8e9500 | | Qwen-3-8B | 18.9 | Not recorded | 6982d2a6a8b01e76cc8e9500 | | MiniMax-M2.1 | 16.7 | Not recorded | 6982d2a6a8b01e76cc8e9500 | | Qwen-3-8B | 14.5 | Not recorded | 6982d2a6a8b01e76cc8e9500 | | MiniMax-M2.1 | 14.4 | Not recorded | 6982d2a6a8b01e76cc8e9500 | | MiniMax-M2.1 | 13.3 | Not recorded | 6982d2a6a8b01e76cc8e9500 | | Qwen-3-8B | 12.2 | Not recorded | 6982d2a6a8b01e76cc8e9500 | | MiniMax-M2.1 | 12.2 | Not recorded | 6982d2a6a8b01e76cc8e9500 | | Qwen-3-8B | 10 | Not recorded | 6982d2a6a8b01e76cc8e9500 | | Qwen-3-8B | 8.9 | Not recorded | 6982d2a6a8b01e76cc8e9500 | ### MiniMax-M2.1 Success Rate: 46.7. Result ID: 699650455698665ec4950da5. [Reporting paper]() Recorded evaluation configuration: {"Intervention Mechanism":"Baseline","Calibration":"N/A"}. This record does not assert independent reproduction. ### GLM-4.7 Success Rate: 34.4. Result ID: 699650455698665ec4950da0. [Reporting paper]() Recorded evaluation configuration: {"Intervention Mechanism":"Baseline","Calibration":"N/A"}. This record does not assert independent reproduction. ### GLM-4.7 Success Rate: 31.1. Result ID: 699650455698665ec4950da4. [Reporting paper]() Recorded evaluation configuration: {"Intervention Mechanism":"Append","Calibration":"Calibrated"}. This record does not assert independent reproduction. ### GLM-4.7 Success Rate: 27.8. Result ID: 699650455698665ec4950da2. [Reporting paper]() Recorded evaluation configuration: {"Intervention Mechanism":"Rollback","Calibration":"Calibrated"}. This record does not assert independent reproduction. ### GLM-4.7 Success Rate: 23.3. Result ID: 699650455698665ec4950da1. [Reporting paper]() Recorded evaluation configuration: {"Intervention Mechanism":"Rollback","Calibration":"Uncalibrated"}. This record does not assert independent reproduction. ### GLM-4.7 Success Rate: 23.3. Result ID: 699650455698665ec4950da3. [Reporting paper]() Recorded evaluation configuration: {"Intervention Mechanism":"Append","Calibration":"Uncalibrated"}. This record does not assert independent reproduction. ### Qwen-3-8B Success Rate: 18.9. Result ID: 699650455698665ec4950d9b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Intervention Mechanism":"Baseline","Calibration":"N/A"}. This record does not assert independent reproduction. ### MiniMax-M2.1 Success Rate: 16.7. Result ID: 699650455698665ec4950da7. [Reporting paper]() Recorded evaluation configuration: {"Intervention Mechanism":"Rollback","Calibration":"Calibrated"}. This record does not assert independent reproduction. ### Qwen-3-8B Success Rate: 14.5. Result ID: 699650455698665ec4950d9c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Intervention Mechanism":"Rollback","Calibration":"Uncalibrated"}. This record does not assert independent reproduction. ### MiniMax-M2.1 Success Rate: 14.4. Result ID: 699650455698665ec4950da9. [Reporting paper]() Recorded evaluation configuration: {"Intervention Mechanism":"Append","Calibration":"Calibrated"}. This record does not assert independent reproduction. ### MiniMax-M2.1 Success Rate: 13.3. Result ID: 699650455698665ec4950da6. [Reporting paper]() Recorded evaluation configuration: {"Intervention Mechanism":"Rollback","Calibration":"Uncalibrated"}. This record does not assert independent reproduction. ### Qwen-3-8B Success Rate: 12.2. Result ID: 699650455698665ec4950d9d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Intervention Mechanism":"Rollback","Calibration":"Calibrated"}. This record does not assert independent reproduction. ### MiniMax-M2.1 Success Rate: 12.2. Result ID: 699650455698665ec4950da8. [Reporting paper]() Recorded evaluation configuration: {"Intervention Mechanism":"Append","Calibration":"Uncalibrated"}. This record does not assert independent reproduction. ### Qwen-3-8B Success Rate: 10. Result ID: 699650455698665ec4950d9f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Intervention Mechanism":"Append","Calibration":"Calibrated"}. This record does not assert independent reproduction. ### Qwen-3-8B Success Rate: 8.9. Result ID: 699650455698665ec4950d9e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Intervention Mechanism":"Append","Calibration":"Uncalibrated"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.