# Sports Video Question Answering on SportsTime Source: [Sports Video Question Answering on SportsTime]() Collection index: [llms.txt]() Data updated: 2026-04-27T06:59:38.126Z Evaluation of model performance on the SportsTime dataset for Sports Video Question Answering, reporting metrics across Perception, Temporal, Tactical, Causal, and Counterfactual dimensions. 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 | Sports Video Question Answering | | Dataset (including any stated split) | SportsTime | | Metric | Perception Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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 - [Perception Score](): Higher is better; unit: SCALAR. - [Temporal Score](): Higher is better; unit: SCALAR. - [Tactical Score](): Higher is better; unit: SCALAR. - [Causal Score](): Higher is better; unit: SCALAR. - [Counterfactual Score](): Higher is better; unit: SCALAR. - [Average Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Perception Score | Result date | Report paper | | --- | --- | --- | --- | | Gemini-2.5-Pro | 39.66 | Not recorded | 69eeed9555a3c32af89f97b1 | | GPT-5 | 38.77 | Not recorded | 69eeed9555a3c32af89f97b1 | | CoTR (full) | 25.12 | Not recorded | 69eeed9555a3c32af89f97b1 | | Qwen3-VL-8B-Instruct | 24.27 | Not recorded | 69eeed9555a3c32af89f97b1 | | Qwen3-VL-4B-Instruct | 23.26 | Not recorded | 69eeed9555a3c32af89f97b1 | | Qwen3-VL-4B-Instruct | 23.26 | Not recorded | 69eeed9555a3c32af89f97b1 | | CoTR (tr-GRPO) | 22.01 | Not recorded | 69eeed9555a3c32af89f97b1 | | InternVL2.5-4B | 21.99 | Not recorded | 69eeed9555a3c32af89f97b1 | | VideoLLaMA-7B | 20.06 | Not recorded | 69eeed9555a3c32af89f97b1 | | Video-R1-7B | 19.26 | Not recorded | 69eeed9555a3c32af89f97b1 | | InternVideo2.5-8B | 18.12 | Not recorded | 69eeed9555a3c32af89f97b1 | | Qwen2.5-VL-3B-Instruct | 16.67 | Not recorded | 69eeed9555a3c32af89f97b1 | | MiniCPM-V4.5-8B | 16.38 | Not recorded | 69eeed9555a3c32af89f97b1 | | MiniCPM-v4-4B | 14.21 | Not recorded | 69eeed9555a3c32af89f97b1 | | LLaVA-OneVision1.5-4B | 13.88 | Not recorded | 69eeed9555a3c32af89f97b1 | | Ovis2-4B | 11.87 | Not recorded | 69eeed9555a3c32af89f97b1 | | GLM-4.6v-Flash-9B | 2.27 | Not recorded | 69eeed9555a3c32af89f97b1 | ### Gemini-2.5-Pro Perception Score: 39.66. Result ID: 69ef092d47f34ce924d4aea0. [Reporting paper]() Recorded evaluation configuration: {"Visual Input":"0.2 fps"}. This record does not assert independent reproduction. ### GPT-5 Perception Score: 38.77. Result ID: 69ef092d47f34ce924d4ae9f. [Reporting paper]() Recorded evaluation configuration: {"Visual Input":"0.2 fps"}. This record does not assert independent reproduction. ### CoTR (full) Perception Score: 25.12. Result ID: 69ef092d47f34ce924d4ae96. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training":"full","Backbone":"Qwen3-VL-4B-Instruct"}. This record does not assert independent reproduction. ### Qwen3-VL-8B-Instruct Perception Score: 24.27. Result ID: 69ef092d47f34ce924d4aea1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Visual Input":"768"}. This record does not assert independent reproduction. ### Qwen3-VL-4B-Instruct Perception Score: 23.26. Result ID: 69ef092d47f34ce924d4ae8f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"4B"}. This record does not assert independent reproduction. ### Qwen3-VL-4B-Instruct Perception Score: 23.26. Result ID: 69ef092d47f34ce924d4aea2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Visual Input":"768"}. This record does not assert independent reproduction. ### CoTR (tr-GRPO) Perception Score: 22.01. Result ID: 69ef092d47f34ce924d4ae95. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training":"tr-GRPO","Backbone":"Qwen3-VL-4B-Instruct"}. This record does not assert independent reproduction. ### InternVL2.5-4B Perception Score: 21.99. Result ID: 69ef092d47f34ce924d4ae91. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"4B"}. This record does not assert independent reproduction. ### VideoLLaMA-7B Perception Score: 20.06. Result ID: 69ef092d47f34ce924d4aea3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Visual Input":"768"}. This record does not assert independent reproduction. ### Video-R1-7B Perception Score: 19.26. Result ID: 69ef092d47f34ce924d4aea5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Visual Input":"768"}. This record does not assert independent reproduction. ### InternVideo2.5-8B Perception Score: 18.12. Result ID: 69ef092d47f34ce924d4aea4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Visual Input":"512"}. This record does not assert independent reproduction. ### Qwen2.5-VL-3B-Instruct Perception Score: 16.67. Result ID: 69ef092d47f34ce924d4ae90. [Reporting paper]() Recorded evaluation configuration: {"Parameters":"3B"}. This record does not assert independent reproduction. ### MiniCPM-V4.5-8B Perception Score: 16.38. Result ID: 69ef092d47f34ce924d4aea6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Visual Input":"512"}. This record does not assert independent reproduction. ### MiniCPM-v4-4B Perception Score: 14.21. Result ID: 69ef092d47f34ce924d4ae92. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"4B"}. This record does not assert independent reproduction. ### LLaVA-OneVision1.5-4B Perception Score: 13.88. Result ID: 69ef092d47f34ce924d4ae94. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"4B"}. This record does not assert independent reproduction. ### Ovis2-4B Perception Score: 11.87. Result ID: 69ef092d47f34ce924d4ae93. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"4B"}. This record does not assert independent reproduction. ### GLM-4.6v-Flash-9B Perception Score: 2.27. Result ID: 69ef092d47f34ce924d4aea7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Visual Input":"512"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.