# Video Temporal Grounding on Charades-STA g43\_s7 (test) Source: [Video Temporal Grounding on Charades-STA g43\_s7 (test)]() Collection index: [llms.txt]() Data updated: 2026-03-10T08:20:53.973Z Evaluation of Video Temporal Grounding performance on the specific g43\_s7 test split of the Charades-STA dataset, measured using R@0.3, R@0.5, R@0.7, and mIoU. 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 | Video Temporal Grounding | | Dataset (including any stated split) | Charades-STA g43\_s7 (test) | | Metric | R@0.5 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 - [R@0.5](): Higher is better; unit: PERCENT. - [R@0.3](): Higher is better; unit: PERCENT. - [R@0.7](): Higher is better; unit: PERCENT. - [mIoU](): Higher is better; unit: PERCENT. ## Recorded results | Method | R@0.5 | Result date | Report paper | | --- | --- | --- | --- | | Qwen2-VL-7B + T2SGrid-FT | 60.6 | Not recorded | 69afa5642d603e6de3e43841 | | TimeSuite | 48.7 | Not recorded | 69afa5642d603e6de3e43841 | | Qwen3-VL-8B + T2SGrid | 47 | Not recorded | 69afa5642d603e6de3e43841 | | Qwen2-VL-7B + T2SGrid | 46.7 | Not recorded | 69afa5642d603e6de3e43841 | | Qwen3-VL-8B | 43.4 | Not recorded | 69afa5642d603e6de3e43841 | | NumPro | 42 | Not recorded | 69afa5642d603e6de3e43841 | | TRACE | 40.3 | Not recorded | 69afa5642d603e6de3e43841 | | GPT-4o + T2SGrid | 36.7 | Not recorded | 69afa5642d603e6de3e43841 | | VTG-LLM | 33.8 | Not recorded | 69afa5642d603e6de3e43841 | | GPT-4o | 32 | Not recorded | 69afa5642d603e6de3e43841 | | HawkEye | 31.4 | Not recorded | 69afa5642d603e6de3e43841 | | GroundingGPT | 29.6 | Not recorded | 69afa5642d603e6de3e43841 | | VTimeLLM | 27.5 | Not recorded | 69afa5642d603e6de3e43841 | | LLaVA-OneVision-1.5-8B + T2SGrid | 26.3 | Not recorded | 69afa5642d603e6de3e43841 | | Momentor | 23 | Not recorded | 69afa5642d603e6de3e43841 | | TimeChat | 22.9 | Not recorded | 69afa5642d603e6de3e43841 | | LLaVA-OneVision-1.5-8B | 6.7 | Not recorded | 69afa5642d603e6de3e43841 | | Qwen2-VL-7B | 5.4 | Not recorded | 69afa5642d603e6de3e43841 | ### Qwen2-VL-7B + T2SGrid-FT R@0.5: 60.6. Result ID: 69afd4636dbb7075b9581dc2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"General Vision-LLMs","Framework":"T2SGrid-FT"}. This record does not assert independent reproduction. ### TimeSuite R@0.5: 48.7. Result ID: 69afd4636dbb7075b9581db7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"VTG-Tuned Vision-LLMs"}. This record does not assert independent reproduction. ### Qwen3-VL-8B + T2SGrid R@0.5: 47. Result ID: 69afd4636dbb7075b9581dbd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"General Vision-LLMs","Framework":"T2SGrid"}. This record does not assert independent reproduction. ### Qwen2-VL-7B + T2SGrid R@0.5: 46.7. Result ID: 69afd4636dbb7075b9581dc1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"General Vision-LLMs","Framework":"T2SGrid"}. This record does not assert independent reproduction. ### Qwen3-VL-8B R@0.5: 43.4. Result ID: 69afd4636dbb7075b9581dbc. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"General Vision-LLMs"}. This record does not assert independent reproduction. ### NumPro R@0.5: 42. Result ID: 69afd4636dbb7075b9581db9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"VTG-Tuned Vision-LLMs"}. This record does not assert independent reproduction. ### TRACE R@0.5: 40.3. Result ID: 69afd4636dbb7075b9581db8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"VTG-Tuned Vision-LLMs"}. This record does not assert independent reproduction. ### GPT-4o + T2SGrid R@0.5: 36.7. Result ID: 69afd4636dbb7075b9581dbb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"General Vision-LLMs","Framework":"T2SGrid"}. This record does not assert independent reproduction. ### VTG-LLM R@0.5: 33.8. Result ID: 69afd4636dbb7075b9581db2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"VTG-Tuned Vision-LLMs"}. This record does not assert independent reproduction. ### GPT-4o R@0.5: 32. Result ID: 69afd4636dbb7075b9581dba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"General Vision-LLMs"}. This record does not assert independent reproduction. ### HawkEye R@0.5: 31.4. Result ID: 69afd4636dbb7075b9581db6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"VTG-Tuned Vision-LLMs"}. This record does not assert independent reproduction. ### GroundingGPT R@0.5: 29.6. Result ID: 69afd4636dbb7075b9581db1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"VTG-Tuned Vision-LLMs"}. This record does not assert independent reproduction. ### VTimeLLM R@0.5: 27.5. Result ID: 69afd4636dbb7075b9581db4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"VTG-Tuned Vision-LLMs"}. This record does not assert independent reproduction. ### LLaVA-OneVision-1.5-8B + T2SGrid R@0.5: 26.3. Result ID: 69afd4636dbb7075b9581dbf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"General Vision-LLMs","Framework":"T2SGrid"}. This record does not assert independent reproduction. ### Momentor R@0.5: 23. Result ID: 69afd4636dbb7075b9581db5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"VTG-Tuned Vision-LLMs"}. This record does not assert independent reproduction. ### TimeChat R@0.5: 22.9. Result ID: 69afd4636dbb7075b9581db3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"VTG-Tuned Vision-LLMs"}. This record does not assert independent reproduction. ### LLaVA-OneVision-1.5-8B R@0.5: 6.7. Result ID: 69afd4636dbb7075b9581dbe. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"General Vision-LLMs"}. This record does not assert independent reproduction. ### Qwen2-VL-7B R@0.5: 5.4. Result ID: 69afd4636dbb7075b9581dc0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"General Vision-LLMs"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.