# Multimodal Reasoning Across University-Level Disciplines on MMMU Source: [Multimodal Reasoning Across University-Level Disciplines on MMMU]() Collection index: [llms.txt]() Data updated: 2026-06-09T07:03:02.110Z Evaluation of model performance on the MMMU dataset focusing on multimodal reasoning capabilities across various university-level disciplines, measured by accuracy and an average 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 reasoning across university-level disciplines | | Dataset (including any stated split) | MMMU | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | MMS-PRM | 54.2 | Not recorded | 6a279de790966ade919bf54c | | InternVL-2.5 | 54.1 | Not recorded | 6a279de790966ade919bf54c | | InternVL2.5-MPO | 53.8 | Not recorded | 6a279de790966ade919bf54c | | Qwen2-VL | 53.7 | Not recorded | 6a279de790966ade919bf54c | | InternVL2.5-MPO + SFT | 53.7 | Not recorded | 6a279de790966ade919bf54c | | Insight-V | 50.2 | Not recorded | 6a279de790966ade919bf54c | | MiniCPM-V-2-6 | 49.8 | Not recorded | 6a279de790966ade919bf54c | | LLaVA-OneVision | 48.8 | Not recorded | 6a279de790966ade919bf54c | | Ovis1.5-LLaMA3 | 48.3 | Not recorded | 6a279de790966ade919bf54c | | IXC-2.5 | 42.9 | Not recorded | 6a279de790966ade919bf54c | | LLaVA-NeXT-LLaMA3 + SFT | 39.6 | Not recorded | 6a279de790966ade919bf54c | | LLaVA-NeXT-LLaMA3 | 36.9 | Not recorded | 6a279de790966ade919bf54c | ### MMS-PRM Accuracy: 54.2. Result ID: 6a27ba6ffbc373592c23f9ea. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"8B"}. This record does not assert independent reproduction. ### InternVL-2.5 Accuracy: 54.1. Result ID: 6a27ba6ffbc373592c23f9e5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"8B"}. This record does not assert independent reproduction. ### InternVL2.5-MPO Accuracy: 53.8. Result ID: 6a27ba6ffbc373592c23f9e8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"8B"}. This record does not assert independent reproduction. ### Qwen2-VL Accuracy: 53.7. Result ID: 6a27ba6ffbc373592c23f9e3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### InternVL2.5-MPO + SFT Accuracy: 53.7. Result ID: 6a27ba6ffbc373592c23f9e9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"8B"}. This record does not assert independent reproduction. ### Insight-V Accuracy: 50.2. Result ID: 6a27ba6ffbc373592c23f9e4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### MiniCPM-V-2-6 Accuracy: 49.8. Result ID: 6a27ba6ffbc373592c23f9e1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"8B"}. This record does not assert independent reproduction. ### LLaVA-OneVision Accuracy: 48.8. Result ID: 6a27ba6ffbc373592c23f9e2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### Ovis1.5-LLaMA3 Accuracy: 48.3. Result ID: 6a27ba6ffbc373592c23f9e0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"8B"}. This record does not assert independent reproduction. ### IXC-2.5 Accuracy: 42.9. Result ID: 6a27ba6ffbc373592c23f9df. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### LLaVA-NeXT-LLaMA3 + SFT Accuracy: 39.6. Result ID: 6a27ba6ffbc373592c23f9e7. [Reporting paper]() Recorded evaluation configuration: {"Size":"8B"}. This record does not assert independent reproduction. ### LLaVA-NeXT-LLaMA3 Accuracy: 36.9. Result ID: 6a27ba6ffbc373592c23f9e6. [Reporting paper]() Recorded evaluation configuration: {"Size":"8B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.