# Visual Mathematical Reasoning on DynaMath worst Source: [Visual Mathematical Reasoning on DynaMath worst]() Collection index: [llms.txt]() Data updated: 2026-03-20T08:33:13.185Z Evaluation of model performance on the DynaMath worst subset for Visual Mathematical Reasoning tasks, measured by 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 | Visual Mathematical Reasoning | | Dataset (including any stated split) | DynaMath worst | | Metric | Score | | Unit | SCALAR | | 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 - [Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Score | Result date | Report paper | | --- | --- | --- | --- | | OpenMMReasoner | 34.9 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | GPT-4o | 34.5 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | Insight-V++ (Qwen2.5-VL + Self-Evolving) | 33.6 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | Open-Vision-Reasoner | 33.5 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | GPT-4o mini | 31.6 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | Insight-V (Qwen2.5-VL + Multi-Agent RL) | 31.4 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | MMR1 | 27.9 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | InternVL3-8B | 23 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | MM-Eureka-Qwen | 23 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | VLAA-Thinker-Qwen2.5 | 22.4 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | Qwen2.5-VL | 21.8 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | LLaVA-OneVision-1.5 | 19.8 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | VL-Rethinker | 17.8 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | OpenVLThinker | 16.8 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | ThinkLite-VL | 16.5 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | LLaVA-OneVision | 9 | Not recorded | 69bcd45d0636e5bf4afc27b3 | ### OpenMMReasoner Score: 34.9. Result ID: 69bd048947f34ce924a70531. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### GPT-4o Score: 34.5. Result ID: 69bd048947f34ce924a70525. [Reporting paper]() Recorded evaluation configuration: {"Size":"-"}. This record does not assert independent reproduction. ### Insight-V++ (Qwen2.5-VL + Self-Evolving) Score: 33.6. Result ID: 69bd048947f34ce924a70534. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### Open-Vision-Reasoner Score: 33.5. Result ID: 69bd048947f34ce924a70530. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### GPT-4o mini Score: 31.6. Result ID: 69bd048947f34ce924a70526. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"-"}. This record does not assert independent reproduction. ### Insight-V (Qwen2.5-VL + Multi-Agent RL) Score: 31.4. Result ID: 69bd048947f34ce924a70533. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### MMR1 Score: 27.9. Result ID: 69bd048947f34ce924a7052d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### InternVL3-8B Score: 23. Result ID: 69bd048947f34ce924a70528. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"8B"}. This record does not assert independent reproduction. ### MM-Eureka-Qwen Score: 23. Result ID: 69bd048947f34ce924a7052f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### VLAA-Thinker-Qwen2.5 Score: 22.4. Result ID: 69bd048947f34ce924a7052a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### Qwen2.5-VL Score: 21.8. Result ID: 69bd048947f34ce924a70532. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### LLaVA-OneVision-1.5 Score: 19.8. Result ID: 69bd048947f34ce924a70529. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"8B"}. This record does not assert independent reproduction. ### VL-Rethinker Score: 17.8. Result ID: 69bd048947f34ce924a7052c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### OpenVLThinker Score: 16.8. Result ID: 69bd048947f34ce924a7052e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### ThinkLite-VL Score: 16.5. Result ID: 69bd048947f34ce924a7052b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### LLaVA-OneVision Score: 9. Result ID: 69bd048947f34ce924a70527. [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.