# Ad-hoc Constraint Execution (Symbolic Constraint) on GENIUS Source: [Ad-hoc Constraint Execution (Symbolic Constraint) on GENIUS]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:59:45.548Z Evaluation of model performance on Ad-hoc Constraint Execution tasks using the GENIUS dataset, measured by constraint satisfaction metrics (RC, VC, AQ). 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 (Symbolic Constraint) | | Dataset (including any stated split) | GENIUS | | Metric | RC | | 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](): Higher is better; unit: PERCENT. - [VC](): Higher is better; unit: PERCENT. - [AQ](): Higher is better; unit: PERCENT. ## Recorded results | Method | RC | Result date | Report paper | | --- | --- | --- | --- | | Nano Banana Pro | 71.38 | Not recorded | 698d5ea8c97a0b3e3b5e3e7e | | SeeDream 4.5 | 62.91 | Not recorded | 698d5ea8c97a0b3e3b5e3e7e | | Nano Banana | 60.46 | Not recorded | 698d5ea8c97a0b3e3b5e3e7e | | GPT-Image | 58.82 | Not recorded | 698d5ea8c97a0b3e3b5e3e7e | | Ours | 36.54 | Not recorded | 698d5ea8c97a0b3e3b5e3e7e | | Qwen-Image | 36.18 | Not recorded | 698d5ea8c97a0b3e3b5e3e7e | | FLUX.2-dev | 35.76 | Not recorded | 698d5ea8c97a0b3e3b5e3e7e | | Emu3.5-Image | 34.97 | Not recorded | 698d5ea8c97a0b3e3b5e3e7e | | Bagel | 29.61 | Not recorded | 698d5ea8c97a0b3e3b5e3e7e | | Omini-Gen2 | 25.33 | Not recorded | 698d5ea8c97a0b3e3b5e3e7e | | GLM-Image | 22.37 | Not recorded | 698d5ea8c97a0b3e3b5e3e7e | | SeeDream 4.0 | 21.57 | Not recorded | 698d5ea8c97a0b3e3b5e3e7e | | NextStep-1 | 11.33 | Not recorded | 698d5ea8c97a0b3e3b5e3e7e | ### Nano Banana Pro RC: 71.38. Result ID: 6998c18c5698665ec424b465. [Reporting paper]() Recorded evaluation configuration: {"Interleaved":true}. This record does not assert independent reproduction. ### SeeDream 4.5 RC: 62.91. Result ID: 6998c18c5698665ec424b469. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Interleaved":false}. This record does not assert independent reproduction. ### Nano Banana RC: 60.46. Result ID: 6998c18c5698665ec424b466. [Reporting paper]() Recorded evaluation configuration: {"Interleaved":true}. This record does not assert independent reproduction. ### GPT-Image RC: 58.82. Result ID: 6998c18c5698665ec424b467. [Reporting paper]() Recorded evaluation configuration: {"Interleaved":false}. This record does not assert independent reproduction. ### Ours RC: 36.54. Result ID: 6998c18c5698665ec424b471. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Interleaved":true}. This record does not assert independent reproduction. ### Qwen-Image RC: 36.18. Result ID: 6998c18c5698665ec424b46a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Interleaved":false}. This record does not assert independent reproduction. ### FLUX.2-dev RC: 35.76. Result ID: 6998c18c5698665ec424b46c. [Reporting paper]() Recorded evaluation configuration: {"Interleaved":false}. This record does not assert independent reproduction. ### Emu3.5-Image RC: 34.97. Result ID: 6998c18c5698665ec424b46e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Interleaved":false}. This record does not assert independent reproduction. ### Bagel RC: 29.61. Result ID: 6998c18c5698665ec424b470. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Interleaved":true}. This record does not assert independent reproduction. ### Omini-Gen2 RC: 25.33. Result ID: 6998c18c5698665ec424b46f. [Reporting paper]() Recorded evaluation configuration: {"Interleaved":false}. This record does not assert independent reproduction. ### GLM-Image RC: 22.37. Result ID: 6998c18c5698665ec424b46b. [Reporting paper]() Recorded evaluation configuration: {"Interleaved":false}. This record does not assert independent reproduction. ### SeeDream 4.0 RC: 21.57. Result ID: 6998c18c5698665ec424b468. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Interleaved":false}. This record does not assert independent reproduction. ### NextStep-1 RC: 11.33. Result ID: 6998c18c5698665ec424b46d. [Reporting paper]() [Method origin 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.