# Scientific Chart Interpretation on CharXiv Reasoning Source: [Scientific Chart Interpretation on CharXiv Reasoning]() Collection index: [llms.txt]() Data updated: 2026-06-23T08:22:15.431Z Evaluation of model performance on the CharXiv Reasoning dataset for the task of Scientific Chart Interpretation, measured by the overall Score. 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 | Scientific Chart Interpretation | | Dataset (including any stated split) | CharXiv Reasoning | | Metric | Overall Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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 - [Overall Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Overall Score | Result date | Report paper | | --- | --- | --- | --- | | Fugu-Ultra | 86.6 | Not recorded | 6a3a12e6206542251d7c6e10 | | Fugu | 85.1 | Not recorded | 6a3a12e6206542251d7c6e10 | | Claude Opus 4.8 | 84.2 | Not recorded | 6a3a12e6206542251d7c6e10 | | GPT-5.5 | 84.1 | Not recorded | 6a3a12e6206542251d7c6e10 | | Gemini 3.1 | 83.3 | Not recorded | 6a3a12e6206542251d7c6e10 | | Insight-V++ (Qwen2.5-VL + Self-Evolving) | 46.8 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | OpenMMReasoner | 46.1 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | Open-Vision-Reasoner | 44.5 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | Insight-V (Qwen2.5-VL + Multi-Agent RL) | 44.5 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | MMR1 | 43.5 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | MM-Eureka-Qwen | 42.4 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | OpenVLThinker | 41 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | InternVL3-8B | 37.6 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | LLaVA-OneVision-1.5 | 37 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | Qwen2.5-VL | 36.4 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | GPT-4o mini | 34.1 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | LLaVA-OneVision | 23.6 | Not recorded | 69bcd45d0636e5bf4afc27b3 | ### Fugu-Ultra Overall Score: 86.6. Result ID: 6a3a422dfbc373592c34ba91. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Fugu Overall Score: 85.1. Result ID: 6a3a422dfbc373592c34ba92. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Claude Opus 4.8 Overall Score: 84.2. Result ID: 6a3a422dfbc373592c34ba93. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-5.5 Overall Score: 84.1. Result ID: 6a3a422dfbc373592c34ba95. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Gemini 3.1 Overall Score: 83.3. Result ID: 6a3a422dfbc373592c34ba94. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Insight-V++ (Qwen2.5-VL + Self-Evolving) Overall Score: 46.8. Result ID: 69bd048947f34ce924a70540. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### OpenMMReasoner Overall Score: 46.1. Result ID: 69bd048947f34ce924a7053d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### Open-Vision-Reasoner Overall Score: 44.5. Result ID: 69bd048947f34ce924a7053c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### Insight-V (Qwen2.5-VL + Multi-Agent RL) Overall Score: 44.5. Result ID: 69bd048947f34ce924a7053f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### MMR1 Overall Score: 43.5. Result ID: 69bd048947f34ce924a70539. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### MM-Eureka-Qwen Overall Score: 42.4. Result ID: 69bd048947f34ce924a7053b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### OpenVLThinker Overall Score: 41. Result ID: 69bd048947f34ce924a7053a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### InternVL3-8B Overall Score: 37.6. Result ID: 69bd048947f34ce924a70537. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"8B"}. This record does not assert independent reproduction. ### LLaVA-OneVision-1.5 Overall Score: 37. Result ID: 69bd048947f34ce924a70538. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"8B"}. This record does not assert independent reproduction. ### Qwen2.5-VL Overall Score: 36.4. Result ID: 69bd048947f34ce924a7053e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### GPT-4o mini Overall Score: 34.1. Result ID: 69bd048947f34ce924a70535. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"-"}. This record does not assert independent reproduction. ### LLaVA-OneVision Overall Score: 23.6. Result ID: 69bd048947f34ce924a70536. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.