# Long-text generation on LongText-Bench ZH Source: [Long-text generation on LongText-Bench ZH]() Collection index: [llms.txt]() Data updated: 2026-05-13T11:35:56.397Z Evaluation of language models on the LongText-Bench ZH dataset for long-text generation tasks, measured using Accuracy. 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 | Long-text generation | | Dataset (including any stated split) | LongText-Bench ZH | | Metric | Accuracy | | Unit | PERCENT | | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Seedream 4.5 | 98.7 | Not recorded | 6a0405eadbc836b87d8279c4 | | JoyAI-Image | 96.3 | Not recorded | 6a0405eadbc836b87d8279c4 | | SenseNova-U1 | 96.2 | Not recorded | 6a0405eadbc836b87d8279c4 | | SenseNova-U1 | 95.5 | Not recorded | 6a0405eadbc836b87d8279c4 | | Nano-Banana-Pro | 94.9 | Not recorded | 6a0405eadbc836b87d8279c4 | | Qwen-Image | 94.6 | Not recorded | 6a0405eadbc836b87d8279c4 | | Z-Image | 93.6 | Not recorded | 6a0405eadbc836b87d8279c4 | | Emu3.5 | 92.8 | Not recorded | 6a0405eadbc836b87d8279c4 | | LongCat-Next | 89.1 | Not recorded | 6a0405eadbc836b87d8279c4 | | InternVL-U | 86 | Not recorded | 6a0405eadbc836b87d8279c4 | | X-Omni | 81.4 | Not recorded | 6a0405eadbc836b87d8279c4 | | GPT-Image-1 | 61.9 | Not recorded | 6a0405eadbc836b87d8279c4 | | NEO-unify | 49.5 | Not recorded | 6a0405eadbc836b87d8279c4 | | BAGEL | 31 | Not recorded | 6a0405eadbc836b87d8279c4 | | OmniGen2 | 5.9 | Not recorded | 6a0405eadbc836b87d8279c4 | | Lumina-DiMOO | 4.7 | Not recorded | 6a0405eadbc836b87d8279c4 | | FLUX.1-dev | 0.5 | Not recorded | 6a0405eadbc836b87d8279c4 | ### Seedream 4.5 Accuracy: 98.7. Result ID: 6a04621a47f34ce924eb491b. [Reporting paper]() Recorded evaluation configuration: {"# Params":"-"}. This record does not assert independent reproduction. ### JoyAI-Image Accuracy: 96.3. Result ID: 6a04621a47f34ce924eb4920. [Reporting paper]() Recorded evaluation configuration: {"# Params":"16B"}. This record does not assert independent reproduction. ### SenseNova-U1 Accuracy: 96.2. Result ID: 6a04621a47f34ce924eb491e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"# Params":"8B"}. This record does not assert independent reproduction. ### SenseNova-U1 Accuracy: 95.5. Result ID: 6a04621a47f34ce924eb4921. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"# Params":"8BA3B"}. This record does not assert independent reproduction. ### Nano-Banana-Pro Accuracy: 94.9. Result ID: 6a04621a47f34ce924eb491c. [Reporting paper]() Recorded evaluation configuration: {"# Params":"-"}. This record does not assert independent reproduction. ### Qwen-Image Accuracy: 94.6. Result ID: 6a04621a47f34ce924eb4922. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Params":"20B"}. This record does not assert independent reproduction. ### Z-Image Accuracy: 93.6. Result ID: 6a04621a47f34ce924eb4923. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"# Params":"6B"}. This record does not assert independent reproduction. ### Emu3.5 Accuracy: 92.8. Result ID: 6a04621a47f34ce924eb491f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Params":"32B"}. This record does not assert independent reproduction. ### LongCat-Next Accuracy: 89.1. Result ID: 6a04621a47f34ce924eb4924. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"# Params":"68BA3B"}. This record does not assert independent reproduction. ### InternVL-U Accuracy: 86. Result ID: 6a04621a47f34ce924eb4926. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"# Params":"1.7B"}. This record does not assert independent reproduction. ### X-Omni Accuracy: 81.4. Result ID: 6a04621a47f34ce924eb4925. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Params":"12B"}. This record does not assert independent reproduction. ### GPT-Image-1 Accuracy: 61.9. Result ID: 6a04621a47f34ce924eb491d. [Reporting paper]() Recorded evaluation configuration: {"# Params":"-"}. This record does not assert independent reproduction. ### NEO-unify Accuracy: 49.5. Result ID: 6a04621a47f34ce924eb4927. [Reporting paper]() Recorded evaluation configuration: {"# Params":"2B"}. This record does not assert independent reproduction. ### BAGEL Accuracy: 31. Result ID: 6a04621a47f34ce924eb492b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"# Params":"7B"}. This record does not assert independent reproduction. ### OmniGen2 Accuracy: 5.9. Result ID: 6a04621a47f34ce924eb4929. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Params":"4B"}. This record does not assert independent reproduction. ### Lumina-DiMOO Accuracy: 4.7. Result ID: 6a04621a47f34ce924eb492a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"# Params":"8B"}. This record does not assert independent reproduction. ### FLUX.1-dev Accuracy: 0.5. Result ID: 6a04621a47f34ce924eb4928. [Reporting paper]() Recorded evaluation configuration: {"# Params":"12B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.