# General Visual Question Answering on HallusionBench Source: [General Visual Question Answering on HallusionBench]() Collection index: [llms.txt]() Data updated: 2026-07-02T08:11:10.975Z Evaluation of model performance on the HallusionBench dataset for General Visual Question Answering, reporting Pass@1. 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 | General visual question answering | | Dataset (including any stated split) | HallusionBench | | Metric | Pass@1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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 - [Pass@1](): Higher is better; unit: PERCENT. ## Recorded results | Method | Pass@1 | Result date | Report paper | | --- | --- | --- | --- | | Gemini-3-Pro High | 69.9 | Not recorded | 6a45f082dc71372d7795a1ae | | Seed2.0 Pro | 68 | Not recorded | 6a45f082dc71372d7795a1ae | | GPT-5.2 High | 67.7 | Not recorded | 6a45f082dc71372d7795a1ae | | Seed2.0 Lite | 66 | Not recorded | 6a45f082dc71372d7795a1ae | | Claude-Opus-4.5 | 65.3 | Not recorded | 6a45f082dc71372d7795a1ae | | Seed2.0 Mini | 65.1 | Not recorded | 6a45f082dc71372d7795a1ae | | Seed1.8 | 63.9 | Not recorded | 6a45f082dc71372d7795a1ae | | Gemini 1.5 Pro | 63.7 | Not recorded | 68fa78791e209131cea788a1 | | Seed 1.5-VL | 60.3 | Not recorded | 68fa78791e209131cea788a1 | | Seed 1.5-VL | 60 | Not recorded | 68fa78791e209131cea788a1 | | Claude 3.7 Sonnet | 58.3 | Not recorded | 68fa78791e209131cea788a1 | | GPT-4o | 56.2 | Not recorded | 68fa78791e209131cea788a1 | | OpenAI o1 | 55.6 | Not recorded | 68fa78791e209131cea788a1 | | Qwen 2.5-VL 72B | 55.2 | Not recorded | 68fa78791e209131cea788a1 | ### Gemini-3-Pro High Pass@1: 69.9. Result ID: 6a461cfe60b88bb33984ab6e. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Seed2.0 Pro Pass@1: 68. Result ID: 6a461cfe60b88bb33984ab72. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-5.2 High Pass@1: 67.7. Result ID: 6a461cfe60b88bb33984ab6d. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Seed2.0 Lite Pass@1: 66. Result ID: 6a461cfe60b88bb33984ab71. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Claude-Opus-4.5 Pass@1: 65.3. Result ID: 6a461cfe60b88bb33984ab6c. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Seed2.0 Mini Pass@1: 65.1. Result ID: 6a461cfe60b88bb33984ab70. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Seed1.8 Pass@1: 63.9. Result ID: 6a461cfe60b88bb33984ab6f. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Gemini 1.5 Pro Pass@1: 63.7. Result ID: 69958c593badfaffe685f969. [Reporting paper]() Recorded evaluation configuration: {"thinking":true,"decoding":"greedy"}. This record does not assert independent reproduction. ### Seed 1.5-VL Pass@1: 60.3. Result ID: 69958c593badfaffe685f967. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"thinking":true,"decoding":"greedy"}. This record does not assert independent reproduction. ### Seed 1.5-VL Pass@1: 60. Result ID: 69958c593badfaffe685f968. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"thinking":false,"decoding":"greedy"}. This record does not assert independent reproduction. ### Claude 3.7 Sonnet Pass@1: 58.3. Result ID: 69958c593badfaffe685f96b. [Reporting paper]() Recorded evaluation configuration: {"thinking":true,"decoding":"sampling"}. This record does not assert independent reproduction. ### GPT-4o Pass@1: 56.2. Result ID: 69958c593badfaffe685f96c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"thinking":false,"decoding":"greedy"}. This record does not assert independent reproduction. ### OpenAI o1 Pass@1: 55.6. Result ID: 69958c593badfaffe685f96a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"thinking":true,"decoding":"greedy"}. This record does not assert independent reproduction. ### Qwen 2.5-VL 72B Pass@1: 55.2. Result ID: 69958c593badfaffe685f96d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"thinking":false,"decoding":"greedy"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.