# Chart Reasoning on CHARXIV reasoning Source: [Chart Reasoning on CHARXIV reasoning]() Collection index: [llms.txt]() Data updated: 2026-05-07T07:45:58.467Z Evaluation of model performance on the CHARXIV reasoning dataset specifically for Chart Reasoning tasks, reporting detailed accuracy breakdowns and token usage. 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 Reasoning | | Dataset (including any stated split) | CHARXIV reasoning | | Metric | Accuracy (All) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 7 of 7 | | 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 (All)](): Higher is better; unit: PERCENT. - [Accuracy (Extr)](): Higher is better; unit: PERCENT. - [Accuracy (First)](): Higher is better; unit: PERCENT. - [Accuracy (Read)](): Higher is better; unit: PERCENT. - [Accuracy (RevR)](): Higher is better; unit: PERCENT. - [Accuracy (Comp)](): Higher is better; unit: PERCENT. - [Accuracy (Freq)](): Higher is better; unit: PERCENT. - [Peak Tokens](): Higher is better; unit: SCALAR. ## Recorded results | Method | Accuracy (All) | Result date | Report paper | | --- | --- | --- | --- | | HierVA | 64.2 | Not recorded | 69fc1c705497b3b670c88419 | | CoT-Plan | 62.4 | Not recorded | 69fc1c705497b3b670c88419 | | CoT | 62.1 | Not recorded | 69fc1c705497b3b670c88419 | | Thinking w/ Images | 58.9 | Not recorded | 69fc1c705497b3b670c88419 | | Thinking w/ Images | 55.3 | Not recorded | 69fc1c705497b3b670c88419 | | Thinking w/ Images | 50.1 | Not recorded | 69fc1c705497b3b670c88419 | | Direct | 45.7 | Not recorded | 69fc1c705497b3b670c88419 | ### HierVA Accuracy (All): 64.2. Result ID: 69fc432647f34ce924deb4bf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Image Tools":"zoom, code","Skills":"dynamic"}. This record does not assert independent reproduction. ### CoT-Plan Accuracy (All): 62.4. Result ID: 69fc432647f34ce924deb4bb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Image Tools":"—","Skills":"—"}. This record does not assert independent reproduction. ### CoT Accuracy (All): 62.1. Result ID: 69fc432647f34ce924deb4ba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Image Tools":"—","Skills":"—"}. This record does not assert independent reproduction. ### Thinking w/ Images Accuracy (All): 58.9. Result ID: 69fc432647f34ce924deb4bc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Image Tools":"zoom","Skills":"—"}. This record does not assert independent reproduction. ### Thinking w/ Images Accuracy (All): 55.3. Result ID: 69fc432647f34ce924deb4be. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Image Tools":"zoom, code","Skills":"fixed"}. This record does not assert independent reproduction. ### Thinking w/ Images Accuracy (All): 50.1. Result ID: 69fc432647f34ce924deb4bd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Image Tools":"zoom, code","Skills":"—"}. This record does not assert independent reproduction. ### Direct Accuracy (All): 45.7. Result ID: 69fc432647f34ce924deb4b9. [Reporting paper]() Recorded evaluation configuration: {"Image Tools":"—","Skills":"—"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.