# React UI Generation on Cookie-Bench Overall Source: [React UI Generation on Cookie-Bench Overall]() Collection index: [llms.txt]() Data updated: 2026-05-29T10:43:44.702Z Evaluation of model performance on generating React User Interfaces using the Cookie-Bench Overall dataset. 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 | React UI Generation | | Dataset (including any stated split) | Cookie-Bench Overall | | Metric | Total Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 26 of 26 | | 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 - [Total Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Total Score | Result date | Report paper | | --- | --- | --- | --- | | Opus 4.7 | 84.2 | Not recorded | 6a191ddfdbd7150506f82ba8 | | Opus 4.7 | 83.3 | Not recorded | 6a191ddfdbd7150506f82ba8 | | Opus 4.6 | 80 | Not recorded | 6a191ddfdbd7150506f82ba8 | | Kimi-K2.6 | 78.9 | Not recorded | 6a191ddfdbd7150506f82ba8 | | Opus 4.6 | 78.9 | Not recorded | 6a191ddfdbd7150506f82ba8 | | GPT-5.4 | 78.6 | Not recorded | 6a191ddfdbd7150506f82ba8 | | Kimi-K2.6 | 78.3 | Not recorded | 6a191ddfdbd7150506f82ba8 | | GPT-5.4 | 77.8 | Not recorded | 6a191ddfdbd7150506f82ba8 | | Mimo-V2-Pro | 76.3 | Not recorded | 6a191ddfdbd7150506f82ba8 | | GLM-5.1 | 76.2 | Not recorded | 6a191ddfdbd7150506f82ba8 | | GLM-5.1 | 76.1 | Not recorded | 6a191ddfdbd7150506f82ba8 | | Qwen3.6-Plus | 75.2 | Not recorded | 6a191ddfdbd7150506f82ba8 | | DS-V4-Pro | 74.6 | Not recorded | 6a191ddfdbd7150506f82ba8 | | Qwen3.6-Plus | 74.4 | Not recorded | 6a191ddfdbd7150506f82ba8 | | Mimo-V2-Pro | 73.9 | Not recorded | 6a191ddfdbd7150506f82ba8 | | Gemini-3.1-Pro | 73.5 | Not recorded | 6a191ddfdbd7150506f82ba8 | | DS-V4-Pro | 73.2 | Not recorded | 6a191ddfdbd7150506f82ba8 | | DS-V4-Flash | 72.6 | Not recorded | 6a191ddfdbd7150506f82ba8 | | Qwen3.6-27B | 70.7 | Not recorded | 6a191ddfdbd7150506f82ba8 | | DS-V4-Flash | 67.9 | Not recorded | 6a191ddfdbd7150506f82ba8 | | Qwen3.6-27B | 67.2 | Not recorded | 6a191ddfdbd7150506f82ba8 | | Gemini-3-Flash | 66.1 | Not recorded | 6a191ddfdbd7150506f82ba8 | | Gemini-3.1-Pro | 64.9 | Not recorded | 6a191ddfdbd7150506f82ba8 | | Gemini-3-Flash | 63.3 | Not recorded | 6a191ddfdbd7150506f82ba8 | | Qwen3.6-35B-A3B | 63.1 | Not recorded | 6a191ddfdbd7150506f82ba8 | | Qwen3.6-35B-A3B | 61.3 | Not recorded | 6a191ddfdbd7150506f82ba8 | ### Opus 4.7 Total Score: 84.2. Result ID: 6a196ce7fbc373592c14787c. [Reporting paper]() Recorded evaluation configuration: {"Generation Mode":"HTML direct chat"}. This record does not assert independent reproduction. ### Opus 4.7 Total Score: 83.3. Result ID: 6a196ce7fbc373592c147855. [Reporting paper]() Recorded evaluation configuration: {"Generation Mode":"React agent scaffold"}. This record does not assert independent reproduction. ### Opus 4.6 Total Score: 80. Result ID: 6a196ce7fbc373592c147854. [Reporting paper]() Recorded evaluation configuration: {"Generation Mode":"React agent scaffold"}. This record does not assert independent reproduction. ### Kimi-K2.6 Total Score: 78.9. Result ID: 6a196ce7fbc373592c14787a. [Reporting paper]() Recorded evaluation configuration: {"Generation Mode":"HTML direct chat"}. This record does not assert independent reproduction. ### Opus 4.6 Total Score: 78.9. Result ID: 6a196ce7fbc373592c14787b. [Reporting paper]() Recorded evaluation configuration: {"Generation Mode":"HTML direct chat"}. This record does not assert independent reproduction. ### GPT-5.4 Total Score: 78.6. Result ID: 6a196ce7fbc373592c147879. [Reporting paper]() Recorded evaluation configuration: {"Generation Mode":"HTML direct chat"}. This record does not assert independent reproduction. ### Kimi-K2.6 Total Score: 78.3. Result ID: 6a196ce7fbc373592c147853. [Reporting paper]() Recorded evaluation configuration: {"Generation Mode":"React agent scaffold"}. This record does not assert independent reproduction. ### GPT-5.4 Total Score: 77.8. Result ID: 6a196ce7fbc373592c147852. [Reporting paper]() Recorded evaluation configuration: {"Generation Mode":"React agent scaffold"}. This record does not assert independent reproduction. ### Mimo-V2-Pro Total Score: 76.3. Result ID: 6a196ce7fbc373592c147851. [Reporting paper]() Recorded evaluation configuration: {"Generation Mode":"React agent scaffold"}. This record does not assert independent reproduction. ### GLM-5.1 Total Score: 76.2. Result ID: 6a196ce7fbc373592c147850. [Reporting paper]() Recorded evaluation configuration: {"Generation Mode":"React agent scaffold"}. This record does not assert independent reproduction. ### GLM-5.1 Total Score: 76.1. Result ID: 6a196ce7fbc373592c147877. [Reporting paper]() Recorded evaluation configuration: {"Generation Mode":"HTML direct chat"}. This record does not assert independent reproduction. ### Qwen3.6-Plus Total Score: 75.2. Result ID: 6a196ce7fbc373592c14784f. [Reporting paper]() Recorded evaluation configuration: {"Generation Mode":"React agent scaffold"}. This record does not assert independent reproduction. ### DS-V4-Pro Total Score: 74.6. Result ID: 6a196ce7fbc373592c147875. [Reporting paper]() Recorded evaluation configuration: {"Generation Mode":"HTML direct chat"}. This record does not assert independent reproduction. ### Qwen3.6-Plus Total Score: 74.4. Result ID: 6a196ce7fbc373592c147876. [Reporting paper]() Recorded evaluation configuration: {"Generation Mode":"HTML direct chat"}. This record does not assert independent reproduction. ### Mimo-V2-Pro Total Score: 73.9. Result ID: 6a196ce7fbc373592c147878. [Reporting paper]() Recorded evaluation configuration: {"Generation Mode":"HTML direct chat"}. This record does not assert independent reproduction. ### Gemini-3.1-Pro Total Score: 73.5. Result ID: 6a196ce7fbc373592c147872. [Reporting paper]() Recorded evaluation configuration: {"Generation Mode":"HTML direct chat"}. This record does not assert independent reproduction. ### DS-V4-Pro Total Score: 73.2. Result ID: 6a196ce7fbc373592c14784e. [Reporting paper]() Recorded evaluation configuration: {"Generation Mode":"React agent scaffold"}. This record does not assert independent reproduction. ### DS-V4-Flash Total Score: 72.6. Result ID: 6a196ce7fbc373592c147874. [Reporting paper]() Recorded evaluation configuration: {"Generation Mode":"HTML direct chat"}. This record does not assert independent reproduction. ### Qwen3.6-27B Total Score: 70.7. Result ID: 6a196ce7fbc373592c147873. [Reporting paper]() Recorded evaluation configuration: {"Generation Mode":"HTML direct chat"}. This record does not assert independent reproduction. ### DS-V4-Flash Total Score: 67.9. Result ID: 6a196ce7fbc373592c14784d. [Reporting paper]() Recorded evaluation configuration: {"Generation Mode":"React agent scaffold"}. This record does not assert independent reproduction. ### Qwen3.6-27B Total Score: 67.2. Result ID: 6a196ce7fbc373592c14784c. [Reporting paper]() Recorded evaluation configuration: {"Generation Mode":"React agent scaffold"}. This record does not assert independent reproduction. ### Gemini-3-Flash Total Score: 66.1. Result ID: 6a196ce7fbc373592c147871. [Reporting paper]() Recorded evaluation configuration: {"Generation Mode":"HTML direct chat"}. This record does not assert independent reproduction. ### Gemini-3.1-Pro Total Score: 64.9. Result ID: 6a196ce7fbc373592c14784b. [Reporting paper]() Recorded evaluation configuration: {"Generation Mode":"React agent scaffold"}. This record does not assert independent reproduction. ### Gemini-3-Flash Total Score: 63.3. Result ID: 6a196ce7fbc373592c14784a. [Reporting paper]() Recorded evaluation configuration: {"Generation Mode":"React agent scaffold"}. This record does not assert independent reproduction. ### Qwen3.6-35B-A3B Total Score: 63.1. Result ID: 6a196ce7fbc373592c147870. [Reporting paper]() Recorded evaluation configuration: {"Generation Mode":"HTML direct chat"}. This record does not assert independent reproduction. ### Qwen3.6-35B-A3B Total Score: 61.3. Result ID: 6a196ce7fbc373592c147849. [Reporting paper]() Recorded evaluation configuration: {"Generation Mode":"React agent scaffold"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.