# Ad-hoc Constraint Execution (Visual Constraint) on GENIUS Source: [Ad-hoc Constraint Execution (Visual Constraint) on GENIUS]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:59:45.758Z Evaluation of model performance on the Ad-hoc Constraint Execution task (Visual Constraint) using the GENIUS dataset, measured by RC, VC, and AQ scores. 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 | Ad-hoc Constraint Execution (Visual Constraint) | | Dataset (including any stated split) | GENIUS | | Metric | RC Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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 - [RC Score](): Higher is better; unit: PERCENT. - [VC Score](): Higher is better; unit: PERCENT. - [AQ Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | RC Score | Result date | Report paper | | --- | --- | --- | --- | | Nano Banana Pro | 76.67 | Not recorded | 698d5ea8c97a0b3e3b5e3e7e | | Nano Banana | 68.33 | Not recorded | 698d5ea8c97a0b3e3b5e3e7e | | SeeDream 4.5 | 58.33 | Not recorded | 698d5ea8c97a0b3e3b5e3e7e | | GPT-Image | 49.17 | Not recorded | 698d5ea8c97a0b3e3b5e3e7e | | SeeDream 4.0 | 40 | Not recorded | 698d5ea8c97a0b3e3b5e3e7e | | FLUX.2-dev | 39.17 | Not recorded | 698d5ea8c97a0b3e3b5e3e7e | | Ours | 30.45 | Not recorded | 698d5ea8c97a0b3e3b5e3e7e | | GLM-Image | 27.5 | Not recorded | 698d5ea8c97a0b3e3b5e3e7e | | Qwen-Image | 26.67 | Not recorded | 698d5ea8c97a0b3e3b5e3e7e | | Emu3.5-Image | 24.17 | Not recorded | 698d5ea8c97a0b3e3b5e3e7e | | Bagel | 22.5 | Not recorded | 698d5ea8c97a0b3e3b5e3e7e | | NextStep-1 | 21.5 | Not recorded | 698d5ea8c97a0b3e3b5e3e7e | | Omini-Gen2 | 11.67 | Not recorded | 698d5ea8c97a0b3e3b5e3e7e | ### Nano Banana Pro RC Score: 76.67. Result ID: 6998c18c5698665ec424b472. [Reporting paper]() Recorded evaluation configuration: {"Interleaved":true}. This record does not assert independent reproduction. ### Nano Banana RC Score: 68.33. Result ID: 6998c18c5698665ec424b473. [Reporting paper]() Recorded evaluation configuration: {"Interleaved":true}. This record does not assert independent reproduction. ### SeeDream 4.5 RC Score: 58.33. Result ID: 6998c18c5698665ec424b476. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Interleaved":false}. This record does not assert independent reproduction. ### GPT-Image RC Score: 49.17. Result ID: 6998c18c5698665ec424b474. [Reporting paper]() Recorded evaluation configuration: {"Interleaved":false}. This record does not assert independent reproduction. ### SeeDream 4.0 RC Score: 40. Result ID: 6998c18c5698665ec424b475. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Interleaved":false}. This record does not assert independent reproduction. ### FLUX.2-dev RC Score: 39.17. Result ID: 6998c18c5698665ec424b479. [Reporting paper]() Recorded evaluation configuration: {"Interleaved":false}. This record does not assert independent reproduction. ### Ours RC Score: 30.45. Result ID: 6998c18c5698665ec424b47e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Interleaved":true}. This record does not assert independent reproduction. ### GLM-Image RC Score: 27.5. Result ID: 6998c18c5698665ec424b478. [Reporting paper]() Recorded evaluation configuration: {"Interleaved":false}. This record does not assert independent reproduction. ### Qwen-Image RC Score: 26.67. Result ID: 6998c18c5698665ec424b477. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Interleaved":false}. This record does not assert independent reproduction. ### Emu3.5-Image RC Score: 24.17. Result ID: 6998c18c5698665ec424b47b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Interleaved":false}. This record does not assert independent reproduction. ### Bagel RC Score: 22.5. Result ID: 6998c18c5698665ec424b47d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Interleaved":true}. This record does not assert independent reproduction. ### NextStep-1 RC Score: 21.5. Result ID: 6998c18c5698665ec424b47a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Interleaved":false}. This record does not assert independent reproduction. ### Omini-Gen2 RC Score: 11.67. Result ID: 6998c18c5698665ec424b47c. [Reporting paper]() Recorded evaluation configuration: {"Interleaved":false}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.