# Multimodal Logical Reasoning on LogicVista (test) Source: [Multimodal Logical Reasoning on LogicVista (test)]() Collection index: [llms.txt]() Data updated: 2026-03-20T08:33:13.154Z Evaluation of model performance on the test split of the LogicVista dataset for Multimodal Logical Reasoning capabilities, 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 | Multimodal Logical Reasoning | | Dataset (including any stated split) | LogicVista (test) | | 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 | | --- | --- | --- | --- | | GPT-4o | 64.4 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | Open-Vision-Reasoner | 54.8 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | Insight-V++ (Qwen2.5-VL + Self-Evolving) | 52.9 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | Insight-V (Qwen2.5-VL + Multi-Agent RL) | 51.7 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | OpenMMReasoner | 50 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | MMR1 | 48.9 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | VLAA-Thinker-Qwen2.5 | 48.5 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | Qwen2.5-VL | 47.9 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | MM-Eureka-Qwen | 46.3 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | LLaVA-OneVision-1.5 | 45.8 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | OpenVLThinker | 44.5 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | InternVL3-8B | 43.6 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | ThinkLite-VL | 42.7 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | VL-Rethinker | 42.7 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | GPT-4o mini | 41.4 | Not recorded | 69bcd45d0636e5bf4afc27b3 | | LLaVA-OneVision | 32 | Not recorded | 69bcd45d0636e5bf4afc27b3 | ### GPT-4o Score: 64.4. Result ID: 69bd048947f34ce924a70515. [Reporting paper]() Recorded evaluation configuration: {"Size":"-"}. This record does not assert independent reproduction. ### Open-Vision-Reasoner Score: 54.8. Result ID: 69bd048947f34ce924a70520. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### Insight-V++ (Qwen2.5-VL + Self-Evolving) Score: 52.9. Result ID: 69bd048947f34ce924a70524. [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) Score: 51.7. Result ID: 69bd048947f34ce924a70523. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### OpenMMReasoner Score: 50. Result ID: 69bd048947f34ce924a70521. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### MMR1 Score: 48.9. Result ID: 69bd048947f34ce924a7051d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### VLAA-Thinker-Qwen2.5 Score: 48.5. Result ID: 69bd048947f34ce924a7051a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### Qwen2.5-VL Score: 47.9. Result ID: 69bd048947f34ce924a70522. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### MM-Eureka-Qwen Score: 46.3. Result ID: 69bd048947f34ce924a7051f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### LLaVA-OneVision-1.5 Score: 45.8. Result ID: 69bd048947f34ce924a70519. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"8B"}. This record does not assert independent reproduction. ### OpenVLThinker Score: 44.5. Result ID: 69bd048947f34ce924a7051e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### InternVL3-8B Score: 43.6. Result ID: 69bd048947f34ce924a70518. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"8B"}. This record does not assert independent reproduction. ### ThinkLite-VL Score: 42.7. Result ID: 69bd048947f34ce924a7051b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### VL-Rethinker Score: 42.7. Result ID: 69bd048947f34ce924a7051c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### GPT-4o mini Score: 41.4. Result ID: 69bd048947f34ce924a70516. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"-"}. This record does not assert independent reproduction. ### LLaVA-OneVision Score: 32. Result ID: 69bd048947f34ce924a70517. [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.