# Chart Understanding on ChartXiv RQ Source: [Chart Understanding on ChartXiv RQ]() Collection index: [llms.txt]() Data updated: 2026-03-05T07:07:22.251Z Evaluation of model performance on the ChartXiv RQ dataset specifically for Chart Understanding tasks, measured using Accuracy and Avg. metrics. 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 | Chart Understanding | | Dataset (including any stated split) | ChartXiv RQ | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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. - [Average Metric](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Gemini2.0-Flash | 61.2 | Not recorded | 68fa7bb11e209131cea89eff | | GPT-4o | 47.1 | Not recorded | 68fa7bb11e209131cea89eff | | VisionZero-Qwen-7B(chart) | 46.6 | Not recorded | 68fa7bb11e209131cea89eff | | Bespoke-MiniChart | 46.2 | Not recorded | 68fa7bb11e209131cea89eff | | Chart-R1-7B | 46.2 | Not recorded | 68fa7bb11e209131cea89eff | | VisionZero-Qwen-7B (Chart) | 45.8 | Not recorded | 68fa7bb11e209131cea89eff | | VisionZero-Qwen-7B (Real-World) | 44.8 | Not recorded | 68fa7bb11e209131cea89eff | | OpenVLThinker-7B | 44.1 | Not recorded | 68fa7bb11e209131cea89eff | | VisionZero-Qwen-7B (CLEVR) | 44.1 | Not recorded | 68fa7bb11e209131cea89eff | | MM-Eureka-Qwen-7B | 43.2 | Not recorded | 68fa7bb11e209131cea89eff | | Qwen2.5VL-7b | 42.5 | Not recorded | 68fa7bb11e209131cea89eff | | Qwen2.5-VL-7B | 42.5 | Not recorded | 68fa7bb11e209131cea89eff | | ViGaL-Snake+Rotation | 41.8 | Not recorded | 68fa7bb11e209131cea89eff | | VLAA-Thinker-7B | 41.3 | Not recorded | 68fa7bb11e209131cea89eff | | ECD-Qwen2.5VL-7b | 40.2 | Not recorded | 68fa7bb11e209131cea89eff | | R1-OneVision-7B | 35.3 | Not recorded | 68fa7bb11e209131cea89eff | ### Gemini2.0-Flash Accuracy: 61.2. Result ID: 69a92b8a6dbb7075b9520cda. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"model\_category":"Proprietary Model"}. This record does not assert independent reproduction. ### GPT-4o Accuracy: 47.1. Result ID: 69a92b8a6dbb7075b9520cd9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"model\_category":"Proprietary Model"}. This record does not assert independent reproduction. ### VisionZero-Qwen-7B(chart) Accuracy: 46.6. Result ID: 69a92b8a6dbb7075b9520c9a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Chart Number":"2.0k","QA Number":"0"}. This record does not assert independent reproduction. ### Bespoke-MiniChart Accuracy: 46.2. Result ID: 69a92b8a6dbb7075b9520c98. [Reporting paper]() Recorded evaluation configuration: {"Chart Number":"13.0k","QA Number":"91k"}. This record does not assert independent reproduction. ### Chart-R1-7B Accuracy: 46.2. Result ID: 69a92b8a6dbb7075b9520c99. [Reporting paper]() Recorded evaluation configuration: {"Chart Number":"21.9k","QA Number":"32.7k"}. This record does not assert independent reproduction. ### VisionZero-Qwen-7B (Chart) Accuracy: 45.8. Result ID: 69a92b8a6dbb7075b9520ce2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_context":"Chart","base\_model":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction. ### VisionZero-Qwen-7B (Real-World) Accuracy: 44.8. Result ID: 69a92b8a6dbb7075b9520ce3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_context":"Real-World","base\_model":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction. ### OpenVLThinker-7B Accuracy: 44.1. Result ID: 69a92b8a6dbb7075b9520cdf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base\_model":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction. ### VisionZero-Qwen-7B (CLEVR) Accuracy: 44.1. Result ID: 69a92b8a6dbb7075b9520ce1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_context":"CLEVR","base\_model":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction. ### MM-Eureka-Qwen-7B Accuracy: 43.2. Result ID: 69a92b8a6dbb7075b9520cdd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base\_model":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction. ### Qwen2.5VL-7b Accuracy: 42.5. Result ID: 69a92b8a6dbb7075b9520c96. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Chart Number":"-","QA Number":"-"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B Accuracy: 42.5. Result ID: 69a92b8a6dbb7075b9520cdb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base\_model":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction. ### ViGaL-Snake+Rotation Accuracy: 41.8. Result ID: 69a92b8a6dbb7075b9520ce0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base\_model":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction. ### VLAA-Thinker-7B Accuracy: 41.3. Result ID: 69a92b8a6dbb7075b9520cde. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base\_model":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction. ### ECD-Qwen2.5VL-7b Accuracy: 40.2. Result ID: 69a92b8a6dbb7075b9520c97. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Chart Number":"10.5k","QA Number":"320k"}. This record does not assert independent reproduction. ### R1-OneVision-7B Accuracy: 35.3. Result ID: 69a92b8a6dbb7075b9520cdc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base\_model":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.