# Target Viewpoint Reproduction on TVRBench 500-task (test) Source: [Target Viewpoint Reproduction on TVRBench 500-task (test)]() Collection index: [llms.txt]() Data updated: 2026-06-02T10:46:49.053Z Evaluation of model performance on the test split of TVRBench 500-task, focusing on Target Viewpoint Reproduction capabilities, measured by success rates, steps, and positional/angular errors. 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 | Target Viewpoint Reproduction | | Dataset (including any stated split) | TVRBench 500-task (test) | | Metric | Overall 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 - [Overall Success Rate](): Higher is better; unit: PERCENT. - [S-e Success Rate](): Higher is better; unit: PERCENT. - [S-h Success Rate](): Higher is better; unit: PERCENT. - [M-e Success Rate](): Higher is better; unit: PERCENT. - [M-h Success Rate](): Higher is better; unit: PERCENT. - [Steps](): Lower is better; unit: SCALAR. - [F-stop Success Rate](): Higher is better; unit: PERCENT. - [Positional Error (\|∆p\|)](): Lower is better; unit: SCALAR. - [Angular Error (\|∆θ\|)](): Lower is better; unit: SCALAR. - [Yaw Error (\|∆ϕ\|)](): Lower is better; unit: SCALAR. ## Recorded results | Method | Overall Success Rate | Result date | Report paper | | --- | --- | --- | --- | | Human | 93 | Not recorded | 6a1e6408dbd7150506f8562a | | Gemini-3.1-Pro | 12 | Not recorded | 6a1e6408dbd7150506f8562a | | GPT-5 | 8 | Not recorded | 6a1e6408dbd7150506f8562a | | GPT-5 | 8 | Not recorded | 6a1e6408dbd7150506f8562a | | Qwen3.5-27B | 7.8 | Not recorded | 6a1e6408dbd7150506f8562a | | Qwen3.6-27B | 7 | Not recorded | 6a1e6408dbd7150506f8562a | | GPT-4o | 5.2 | Not recorded | 6a1e6408dbd7150506f8562a | | Qwen3.6-35B-A3B | 4.8 | Not recorded | 6a1e6408dbd7150506f8562a | | Qwen3.5-35B-A3B | 3.8 | Not recorded | 6a1e6408dbd7150506f8562a | | Qwen3.5-27B | 3.2 | Not recorded | 6a1e6408dbd7150506f8562a | | Qwen3.6-27B | 3.2 | Not recorded | 6a1e6408dbd7150506f8562a | | Qwen3.5-9B | 2.8 | Not recorded | 6a1e6408dbd7150506f8562a | | GPT-4o | 2.8 | Not recorded | 6a1e6408dbd7150506f8562a | | Qwen3.5-35B-A3B | 0.8 | Not recorded | 6a1e6408dbd7150506f8562a | | Qwen3.6-35B-A3B | 0.2 | Not recorded | 6a1e6408dbd7150506f8562a | | Qwen3.5-9B | 0 | Not recorded | 6a1e6408dbd7150506f8562a | ### Human Overall Success Rate: 93. Result ID: 6a1eb38afbc373592c199de4. [Reporting paper]() Recorded evaluation configuration: {"Sample size":"five participants","Subset":"balanced 100-task subset"}. This record does not assert independent reproduction. ### Gemini-3.1-Pro Overall Success Rate: 12. Result ID: 6a1eb38afbc373592c199de3. [Reporting paper]() Recorded evaluation configuration: {"Memory representation":"Action-Only (AO)","Decoding":"lowest temperature"}. This record does not assert independent reproduction. ### GPT-5 Overall Success Rate: 8. Result ID: 6a1eb38afbc373592c199de1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Memory representation":"Visual-Action (VA)","Decoding":"lowest temperature"}. This record does not assert independent reproduction. ### GPT-5 Overall Success Rate: 8. Result ID: 6a1eb38afbc373592c199de2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Memory representation":"Action-Only (AO)","Decoding":"lowest temperature"}. This record does not assert independent reproduction. ### Qwen3.5-27B Overall Success Rate: 7.8. Result ID: 6a1eb38afbc373592c199dd8. [Reporting paper]() Recorded evaluation configuration: {"Memory representation":"Action-Only (AO)","Backbone":"Qwen3.5","Parameters":"27B","Decoding":"greedy"}. This record does not assert independent reproduction. ### Qwen3.6-27B Overall Success Rate: 7. Result ID: 6a1eb38afbc373592c199ddc. [Reporting paper]() Recorded evaluation configuration: {"Memory representation":"Action-Only (AO)","Backbone":"Qwen3.6","Parameters":"27B","Decoding":"greedy"}. This record does not assert independent reproduction. ### GPT-4o Overall Success Rate: 5.2. Result ID: 6a1eb38afbc373592c199de0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Memory representation":"Action-Only (AO)","Decoding":"lowest temperature"}. This record does not assert independent reproduction. ### Qwen3.6-35B-A3B Overall Success Rate: 4.8. Result ID: 6a1eb38afbc373592c199dde. [Reporting paper]() Recorded evaluation configuration: {"Memory representation":"Action-Only (AO)","Type":"MoE","Decoding":"greedy"}. This record does not assert independent reproduction. ### Qwen3.5-35B-A3B Overall Success Rate: 3.8. Result ID: 6a1eb38afbc373592c199dda. [Reporting paper]() Recorded evaluation configuration: {"Memory representation":"Action-Only (AO)","Type":"MoE","Decoding":"greedy"}. This record does not assert independent reproduction. ### Qwen3.5-27B Overall Success Rate: 3.2. Result ID: 6a1eb38afbc373592c199dd7. [Reporting paper]() Recorded evaluation configuration: {"Memory representation":"Visual-Action (VA)","Backbone":"Qwen3.5","Parameters":"27B","Decoding":"greedy"}. This record does not assert independent reproduction. ### Qwen3.6-27B Overall Success Rate: 3.2. Result ID: 6a1eb38afbc373592c199ddb. [Reporting paper]() Recorded evaluation configuration: {"Memory representation":"Visual-Action (VA)","Backbone":"Qwen3.6","Parameters":"27B","Decoding":"greedy"}. This record does not assert independent reproduction. ### Qwen3.5-9B Overall Success Rate: 2.8. Result ID: 6a1eb38afbc373592c199dd6. [Reporting paper]() Recorded evaluation configuration: {"Memory representation":"Action-Only (AO)","Backbone":"Qwen3.5","Parameters":"9B","Decoding":"greedy"}. This record does not assert independent reproduction. ### GPT-4o Overall Success Rate: 2.8. Result ID: 6a1eb38afbc373592c199ddf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Memory representation":"Visual-Action (VA)","Decoding":"lowest temperature"}. This record does not assert independent reproduction. ### Qwen3.5-35B-A3B Overall Success Rate: 0.8. Result ID: 6a1eb38afbc373592c199dd9. [Reporting paper]() Recorded evaluation configuration: {"Memory representation":"Visual-Action (VA)","Type":"MoE","Decoding":"greedy"}. This record does not assert independent reproduction. ### Qwen3.6-35B-A3B Overall Success Rate: 0.2. Result ID: 6a1eb38afbc373592c199ddd. [Reporting paper]() Recorded evaluation configuration: {"Memory representation":"Visual-Action (VA)","Type":"MoE","Decoding":"greedy"}. This record does not assert independent reproduction. ### Qwen3.5-9B Overall Success Rate: 0. Result ID: 6a1eb38afbc373592c199dd5. [Reporting paper]() Recorded evaluation configuration: {"Memory representation":"Visual-Action (VA)","Backbone":"Qwen3.5","Parameters":"9B","Decoding":"greedy"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.