# Agent Performance on AgentNoiseBench-Vita Noisy setting 1.0 (test) Source: [Agent Performance on AgentNoiseBench-Vita Noisy setting 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-05-27T10:13:00.796Z Evaluation of agent performance metrics on the AgentNoiseBench-Vita dataset under Noisy setting 1.0, using the test split. Metrics focus on Delivery, In-Store, and OTA performance measured using 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 | Agent Performance | | Dataset (including any stated split) | AgentNoiseBench-Vita Noisy setting 1.0 (test) | | Metric | Delivery Avg@4 Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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 - [Delivery Avg@4 Score](): Higher is better; unit: SCALAR. - [Delivery Pass@4 Score](): Higher is better; unit: SCALAR. - [In-Store Avg@4 Score](): Higher is better; unit: SCALAR. - [In-Store Pass@4 Score](): Higher is better; unit: SCALAR. - [OTA Avg@4 Score](): Higher is better; unit: SCALAR. - [OTA Pass@4 Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Delivery Avg@4 Score | Result date | Report paper | | --- | --- | --- | --- | | NoisyAgent | 28.75 | Not recorded | 6a167ad3dbd7150506f80299 | | DAPO | 24 | Not recorded | 6a167ad3dbd7150506f80299 | | GSPO | 23.75 | Not recorded | 6a167ad3dbd7150506f80299 | | GRPO | 23.25 | Not recorded | 6a167ad3dbd7150506f80299 | | NoisyAgent | 21.5 | Not recorded | 6a167ad3dbd7150506f80299 | | Qwen3-32B | 19.5 | Not recorded | 6a167ad3dbd7150506f80299 | | GSPO | 16 | Not recorded | 6a167ad3dbd7150506f80299 | | DAPO | 15.75 | Not recorded | 6a167ad3dbd7150506f80299 | | GRPO | 15.25 | Not recorded | 6a167ad3dbd7150506f80299 | | Qwen3-8B | 11.75 | Not recorded | 6a167ad3dbd7150506f80299 | ### NoisyAgent Delivery Avg@4 Score: 28.75. Result ID: 6a16c399fbc373592c1080c6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Model":"Qwen3-32B","Training Method":"NoisyAgent"}. This record does not assert independent reproduction. ### DAPO Delivery Avg@4 Score: 24. Result ID: 6a16c399fbc373592c1080c4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Model":"Qwen3-32B","Training Method":"DAPO"}. This record does not assert independent reproduction. ### GSPO Delivery Avg@4 Score: 23.75. Result ID: 6a16c399fbc373592c1080c5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Model":"Qwen3-32B","Training Method":"GSPO"}. This record does not assert independent reproduction. ### GRPO Delivery Avg@4 Score: 23.25. Result ID: 6a16c399fbc373592c1080c3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone Model":"Qwen3-32B","Training Method":"GRPO"}. This record does not assert independent reproduction. ### NoisyAgent Delivery Avg@4 Score: 21.5. Result ID: 6a16c399fbc373592c1080c1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Model":"Qwen3-8B","Training Method":"NoisyAgent"}. This record does not assert independent reproduction. ### Qwen3-32B Delivery Avg@4 Score: 19.5. Result ID: 6a16c399fbc373592c1080c2. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"Qwen3-32B","Training Method":"Base"}. This record does not assert independent reproduction. ### GSPO Delivery Avg@4 Score: 16. Result ID: 6a16c399fbc373592c1080c0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Model":"Qwen3-8B","Training Method":"GSPO"}. This record does not assert independent reproduction. ### DAPO Delivery Avg@4 Score: 15.75. Result ID: 6a16c399fbc373592c1080bf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Model":"Qwen3-8B","Training Method":"DAPO"}. This record does not assert independent reproduction. ### GRPO Delivery Avg@4 Score: 15.25. Result ID: 6a16c399fbc373592c1080be. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone Model":"Qwen3-8B","Training Method":"GRPO"}. This record does not assert independent reproduction. ### Qwen3-8B Delivery Avg@4 Score: 11.75. Result ID: 6a16c399fbc373592c1080bd. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"Qwen3-8B","Training Method":"Base"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.