# Task progression failure detection on Cover Object (Combined) Source: [Task progression failure detection on Cover Object (Combined)]() Collection index: [llms.txt]() Data updated: 2026-03-13T07:48:16.179Z Evaluation of Task progression failure detection performance using the Cover Object (Combined) dataset, reporting metrics such as True Positive Rate (TPR), True Negative Rate (TNR), and Accuracy. 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 | Task progression failure detection | | Dataset (including any stated split) | Cover Object (Combined) | | Metric | TPR | | 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 - [TPR](): Higher is better; unit: PERCENT. - [TNR](): Higher is better; unit: PERCENT. - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | TPR | Result date | Report paper | | --- | --- | --- | --- | | GPT-4o Image QA | 100 | Not recorded | 69b399e80636e5bf4afbc8cd | | GPT-4o Video QA | 100 | Not recorded | 69b399e80636e5bf4afbc8cd | | Gemini 1.5 Pro Video QA | 100 | Not recorded | 69b399e80636e5bf4afbc8cd | | Claude 3.5 Sonnet Video QA + Success Video | 94 | Not recorded | 69b399e80636e5bf4afbc8cd | | Gemini 1.5 Pro Image QA | 91 | Not recorded | 69b399e80636e5bf4afbc8cd | | Sentinel (STAC MMD\* + Claude 3.5 Sonnet Prompt Ensemble\*) | 88 | Not recorded | 69b399e80636e5bf4afbc8cd | | Claude 3.5 Sonnet Prompt Ensemble\* | 85 | Not recorded | 69b399e80636e5bf4afbc8cd | | Sentinel (STAC MMD\* + Claude 3.5 Sonnet Video QA) | 82 | Not recorded | 69b399e80636e5bf4afbc8cd | | Claude 3.5 Sonnet Video QA | 79 | Not recorded | 69b399e80636e5bf4afbc8cd | | Claude 3.5 Sonnet Video QA + Goal Images | 76 | Not recorded | 69b399e80636e5bf4afbc8cd | | Claude 3.5 Sonnet Image QA | 71 | Not recorded | 69b399e80636e5bf4afbc8cd | | STAC MMD\* | 12 | Not recorded | 69b399e80636e5bf4afbc8cd | | Temporal Non-Distr. Min. | 9 | Not recorded | 69b399e80636e5bf4afbc8cd | | STAC For. KL | 6 | Not recorded | 69b399e80636e5bf4afbc8cd | | STAC Rev. KL | 6 | Not recorded | 69b399e80636e5bf4afbc8cd | | Diffusion Output Variance | 0 | Not recorded | 69b399e80636e5bf4afbc8cd | ### GPT-4o Image QA TPR: 100. Result ID: 69b3c07a47f34ce9249d7cfc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"modality":"Image QA"}. This record does not assert independent reproduction. ### GPT-4o Video QA TPR: 100. Result ID: 69b3c07a47f34ce9249d7cfd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"modality":"Video QA"}. This record does not assert independent reproduction. ### Gemini 1.5 Pro Video QA TPR: 100. Result ID: 69b3c07a47f34ce9249d7cff. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"modality":"Video QA"}. This record does not assert independent reproduction. ### Claude 3.5 Sonnet Video QA + Success Video TPR: 94. Result ID: 69b3c07a47f34ce9249d7d02. [Reporting paper]() Recorded evaluation configuration: {"modality":"Video QA","context":"Success Video"}. This record does not assert independent reproduction. ### Gemini 1.5 Pro Image QA TPR: 91. Result ID: 69b3c07a47f34ce9249d7cfe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"modality":"Image QA"}. This record does not assert independent reproduction. ### Sentinel (STAC MMD\* + Claude 3.5 Sonnet Prompt Ensemble\*) TPR: 88. Result ID: 69b3c07a47f34ce9249d7d06. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"components":"STAC MMD\* + Claude 3.5 Sonnet Prompt Ensemble\*"}. This record does not assert independent reproduction. ### Claude 3.5 Sonnet Prompt Ensemble\* TPR: 85. Result ID: 69b3c07a47f34ce9249d7d04. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"strategy":"Prompt Ensemble"}. This record does not assert independent reproduction. ### Sentinel (STAC MMD\* + Claude 3.5 Sonnet Video QA) TPR: 82. Result ID: 69b3c07a47f34ce9249d7d05. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"components":"STAC MMD\* + Claude 3.5 Sonnet Video QA"}. This record does not assert independent reproduction. ### Claude 3.5 Sonnet Video QA TPR: 79. Result ID: 69b3c07a47f34ce9249d7d01. [Reporting paper]() Recorded evaluation configuration: {"modality":"Video QA"}. This record does not assert independent reproduction. ### Claude 3.5 Sonnet Video QA + Goal Images TPR: 76. Result ID: 69b3c07a47f34ce9249d7d03. [Reporting paper]() Recorded evaluation configuration: {"modality":"Video QA","context":"Goal Images"}. This record does not assert independent reproduction. ### Claude 3.5 Sonnet Image QA TPR: 71. Result ID: 69b3c07a47f34ce9249d7d00. [Reporting paper]() Recorded evaluation configuration: {"modality":"Image QA"}. This record does not assert independent reproduction. ### STAC MMD\* TPR: 12. Result ID: 69b3c07a47f34ce9249d7cfb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"variant":"MMD"}. This record does not assert independent reproduction. ### Temporal Non-Distr. Min. TPR: 9. Result ID: 69b3c07a47f34ce9249d7cf7. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### STAC For. KL TPR: 6. Result ID: 69b3c07a47f34ce9249d7cf9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"variant":"Forward KL"}. This record does not assert independent reproduction. ### STAC Rev. KL TPR: 6. Result ID: 69b3c07a47f34ce9249d7cfa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"variant":"Reverse KL"}. This record does not assert independent reproduction. ### Diffusion Output Variance TPR: 0. Result ID: 69b3c07a47f34ce9249d7cf8. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.