# Web Task Completion on MiniWoB++ Held-out Goals (test) Source: [Web Task Completion on MiniWoB++ Held-out Goals (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:05:27.417Z Evaluation of web agent performance on the specific held-out goals subset of the MiniWoB++ benchmark, measured by success rate. 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 | Web Task Completion | | Dataset (including any stated split) | MiniWoB++ Held-out Goals (test) | | Metric | Success Rate | | 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 - [Success Rate](): Higher is better; unit: PERCENT. ## Recorded results | Method | Success Rate | Result date | Report paper | | --- | --- | --- | --- | | Claude-3.5-Sonnet | 70.5 | Not recorded | 68fa79d41e209131cea7f95b | | o1-Mini | 69.7 | Not recorded | 68fa79d41e209131cea7f95b | | Llama-3.1-8B SFT+RL (Ours) | 67.2 | Not recorded | 68fa79d41e209131cea7f95b | | Llama-3.1-405B-Instruct | 65.9 | Not recorded | 68fa79d41e209131cea7f95b | | GPT-4o | 65.7 | Not recorded | 68fa79d41e209131cea7f95b | | Qwen-2.5-7B SFT+RL (Ours) | 65 | Not recorded | 68fa79d41e209131cea7f95b | | Llama-3.3-70B Instruct (Teacher) | 63.2 | Not recorded | 68fa79d41e209131cea7f95b | | Qwen-2.5-72B Instruct (Teacher) | 61 | Not recorded | 68fa79d41e209131cea7f95b | | Llama-3.1-70B-Instruct | 57 | Not recorded | 68fa79d41e209131cea7f95b | | Qwen-2.5-7B SFT (Ours) | 57 | Not recorded | 68fa79d41e209131cea7f95b | | GPT-4o-Mini | 56.2 | Not recorded | 68fa79d41e209131cea7f95b | | Llama-3.1-8B SFT (Ours) | 55.2 | Not recorded | 68fa79d41e209131cea7f95b | | Qwen-2.5-7B RL (Ours) | 52.5 | Not recorded | 68fa79d41e209131cea7f95b | | Llama-3.1-8B RL (Ours) | 43.5 | Not recorded | 68fa79d41e209131cea7f95b | | Qwen-2.5-7B Instruct (Student) | 32.8 | Not recorded | 68fa79d41e209131cea7f95b | | Llama-3.1-8B Instruct (Student) | 29.5 | Not recorded | 68fa79d41e209131cea7f95b | ### Claude-3.5-Sonnet Success Rate: 70.5. Result ID: 699a631c5698665ec4eb31a8. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"Claude-3.5-Sonnet","Training Protocol":"Instruct","Model Role":"Baseline"}. This record does not assert independent reproduction. ### o1-Mini Success Rate: 69.7. Result ID: 699a631c5698665ec4eb31ac. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"o1-Mini","Training Protocol":"Instruct","Model Role":"Baseline"}. This record does not assert independent reproduction. ### Llama-3.1-8B SFT+RL (Ours) Success Rate: 67.2. Result ID: 699a631c5698665ec4eb31b2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Model":"Llama-3.1-8B","Training Protocol":"SFT+RL","Model Role":"Agent"}. This record does not assert independent reproduction. ### Llama-3.1-405B-Instruct Success Rate: 65.9. Result ID: 699a631c5698665ec4eb31ad. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"Llama-3.1-405B","Training Protocol":"Instruct","Model Role":"Baseline"}. This record does not assert independent reproduction. ### GPT-4o Success Rate: 65.7. Result ID: 699a631c5698665ec4eb31a9. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"GPT-4o","Training Protocol":"Instruct","Model Role":"Baseline"}. This record does not assert independent reproduction. ### Qwen-2.5-7B SFT+RL (Ours) Success Rate: 65. Result ID: 699a631c5698665ec4eb31b7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Model":"Qwen-2.5-7B","Training Protocol":"SFT+RL","Model Role":"Agent"}. This record does not assert independent reproduction. ### Llama-3.3-70B Instruct (Teacher) Success Rate: 63.2. Result ID: 699a631c5698665ec4eb31ae. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"Llama-3.3-70B","Training Protocol":"Instruct","Model Role":"Teacher"}. This record does not assert independent reproduction. ### Qwen-2.5-72B Instruct (Teacher) Success Rate: 61. Result ID: 699a631c5698665ec4eb31b3. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"Qwen-2.5-72B","Training Protocol":"Instruct","Model Role":"Teacher"}. This record does not assert independent reproduction. ### Llama-3.1-70B-Instruct Success Rate: 57. Result ID: 699a631c5698665ec4eb31ab. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"Llama-3.1-70B","Training Protocol":"Instruct","Model Role":"Baseline"}. This record does not assert independent reproduction. ### Qwen-2.5-7B SFT (Ours) Success Rate: 57. Result ID: 699a631c5698665ec4eb31b6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Model":"Qwen-2.5-7B","Training Protocol":"SFT","Model Role":"Agent"}. This record does not assert independent reproduction. ### GPT-4o-Mini Success Rate: 56.2. Result ID: 699a631c5698665ec4eb31aa. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"GPT-4o-Mini","Training Protocol":"Instruct","Model Role":"Baseline"}. This record does not assert independent reproduction. ### Llama-3.1-8B SFT (Ours) Success Rate: 55.2. Result ID: 699a631c5698665ec4eb31b1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Model":"Llama-3.1-8B","Training Protocol":"SFT","Model Role":"Agent"}. This record does not assert independent reproduction. ### Qwen-2.5-7B RL (Ours) Success Rate: 52.5. Result ID: 699a631c5698665ec4eb31b5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Model":"Qwen-2.5-7B","Training Protocol":"RL","Model Role":"Agent"}. This record does not assert independent reproduction. ### Llama-3.1-8B RL (Ours) Success Rate: 43.5. Result ID: 699a631c5698665ec4eb31b0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Model":"Llama-3.1-8B","Training Protocol":"RL","Model Role":"Agent"}. This record does not assert independent reproduction. ### Qwen-2.5-7B Instruct (Student) Success Rate: 32.8. Result ID: 699a631c5698665ec4eb31b4. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"Qwen-2.5-7B","Training Protocol":"Instruct","Model Role":"Student"}. This record does not assert independent reproduction. ### Llama-3.1-8B Instruct (Student) Success Rate: 29.5. Result ID: 699a631c5698665ec4eb31af. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"Llama-3.1-8B","Training Protocol":"Instruct","Model Role":"Student"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.