# VLM-as-Judge Evaluation on ArcBench VLM-as-Judge Closed Source: [VLM-as-Judge Evaluation on ArcBench VLM-as-Judge Closed]() Collection index: [llms.txt]() Data updated: 2026-04-15T07:42:16.464Z Evaluation of Vision-Language Model (VLM) performance when acting as a judge on the closed version of the ArcBench dataset, reporting metrics such as TQ, NF, VL, and VT. 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 | VLM-as-Judge Evaluation | | Dataset (including any stated split) | ArcBench VLM-as-Judge Closed | | Metric | TQ | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 15 of 15 | | 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 - [TQ](): Higher is better; unit: PERCENT. - [NF](): Higher is better; unit: PERCENT. - [VL](): Higher is better; unit: PERCENT. - [VT](): Higher is better; unit: PERCENT. ## Recorded results | Method | TQ | Result date | Report paper | | --- | --- | --- | --- | | HTML | 58.5 | Not recorded | 69df1b987d0172140ec7b92e | | ArcDeck | 53.62 | Not recorded | 69df1b987d0172140ec7b92e | | HTML | 48.62 | Not recorded | 69df1b987d0172140ec7b92e | | ArcDeck | 46.5 | Not recorded | 69df1b987d0172140ec7b92e | | SlideGen | 42.5 | Not recorded | 69df1b987d0172140ec7b92e | | P2Poster | 36.5 | Not recorded | 69df1b987d0172140ec7b92e | | SlideGen | 36.17 | Not recorded | 69df1b987d0172140ec7b92e | | P2Poster | 35.17 | Not recorded | 69df1b987d0172140ec7b92e | | ArcDeck | 24.38 | Not recorded | 69df1b987d0172140ec7b92e | | PPTAgent | 19.25 | Not recorded | 69df1b987d0172140ec7b92e | | PPTAgent | 16.5 | Not recorded | 69df1b987d0172140ec7b92e | | PPTAgent | 12.62 | Not recorded | 69df1b987d0172140ec7b92e | | P2Poster | 11.12 | Not recorded | 69df1b987d0172140ec7b92e | | SlideGen | 9.62 | Not recorded | 69df1b987d0172140ec7b92e | | HTML | 7.25 | Not recorded | 69df1b987d0172140ec7b92e | ### HTML TQ: 58.5. Result ID: 69df404547f34ce924c7b7c9. [Reporting paper]() Recorded evaluation configuration: {"Generation Model":"GPT-5"}. This record does not assert independent reproduction. ### ArcDeck TQ: 53.62. Result ID: 69df404547f34ce924c7b7d7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Generation Model":"Qwen-3-VL-32B-Instruct"}. This record does not assert independent reproduction. ### HTML TQ: 48.62. Result ID: 69df404547f34ce924c7b7d3. [Reporting paper]() Recorded evaluation configuration: {"Generation Model":"Qwen-3-VL-32B-Instruct"}. This record does not assert independent reproduction. ### ArcDeck TQ: 46.5. Result ID: 69df404547f34ce924c7b7cd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Generation Model":"GPT-5"}. This record does not assert independent reproduction. ### SlideGen TQ: 42.5. Result ID: 69df404547f34ce924c7b7d6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generation Model":"Qwen-3-VL-32B-Instruct"}. This record does not assert independent reproduction. ### P2Poster TQ: 36.5. Result ID: 69df404547f34ce924c7b7d4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generation Model":"Qwen-3-VL-32B-Instruct"}. This record does not assert independent reproduction. ### SlideGen TQ: 36.17. Result ID: 69df404547f34ce924c7b7cc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generation Model":"GPT-5"}. This record does not assert independent reproduction. ### P2Poster TQ: 35.17. Result ID: 69df404547f34ce924c7b7ca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generation Model":"GPT-5"}. This record does not assert independent reproduction. ### ArcDeck TQ: 24.38. Result ID: 69df404547f34ce924c7b7d2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Generation Model":"GPT-4o"}. This record does not assert independent reproduction. ### PPTAgent TQ: 19.25. Result ID: 69df404547f34ce924c7b7d5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generation Model":"Qwen-3-VL-32B-Instruct"}. This record does not assert independent reproduction. ### PPTAgent TQ: 16.5. Result ID: 69df404547f34ce924c7b7cb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generation Model":"GPT-5"}. This record does not assert independent reproduction. ### PPTAgent TQ: 12.62. Result ID: 69df404547f34ce924c7b7d0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generation Model":"GPT-4o"}. This record does not assert independent reproduction. ### P2Poster TQ: 11.12. Result ID: 69df404547f34ce924c7b7cf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generation Model":"GPT-4o"}. This record does not assert independent reproduction. ### SlideGen TQ: 9.62. Result ID: 69df404547f34ce924c7b7d1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generation Model":"GPT-4o"}. This record does not assert independent reproduction. ### HTML TQ: 7.25. Result ID: 69df404547f34ce924c7b7ce. [Reporting paper]() Recorded evaluation configuration: {"Generation Model":"GPT-4o"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.