Multimodal benchmark # Video-MME leaderboard > Video-MME results for 15 AI models, led by video-SALMONN 2+ at 79.7%. What the benchmark measures, who runs it, and a source for every score. - Canonical page: https://noometry.com/benchmarks/video-mme - Last updated: 2026-10-10 - Title: Video-MME Leaderboard (October 2026): Scores by Model As of October 2026, video-SALMONN 2+ has the highest published Video-MME score on Noometry at 79.7%, out of 15 models with results. Last verified October 10, 2026 ## About Video-MME Multiple-choice questions about short, medium and long videos. Scores here are without subtitles. - **Category:** [Multimodal](https://noometry.com/best/multimodal) - **Introduced:** 2024 - **Size:** 900 videos - **Format:** Multiple choice - **Unit:** Percent (random guessing ≈ 25%) - **Official site:** [video-mme.github.io](https://video-mme.github.io) ## Top 15 models Top models on Video-MME 1. video-SALMONN 2+ 79.7% 2. Gemini 1.5 Pro (May 2024) 75% 3. Gemini 1.5 Pro (May 2024) 75% 4. Qwen2.5-VL 72B Instruct 73.5% 5. InternVL2\_5-78B 72.1% 6. GPT-4o 71.9% 7. GPT-4o 71.9% 8. Gemini 1.5 Flash (May 2024) 70.3% 9. GPT-4o mini 64.8% 10. NVILA 8B 64.2% 11. InternVL2-40B 61.2% 12. Claude 3.5 Sonnet 60% 13. Claude 3.5 Sonnet 60% 14. GPT-4V 59.9% 15. Qwen-VL Max 51.3% 16. 4050607080 Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise) ## All results Video-MME results by model | # | Model | Provider | Score | Setting | Source | Date | | --- | --- | --- | --- | --- | --- | --- | | 1 | [video-SALMONN 2+](https://noometry.com/models/video-salmonn-2-plus) | [![](/logos/bytedance.svg) ByteDance Seed](https://noometry.com/providers/bytedance) | 79.7% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 2 | [Gemini 1.5 Pro (May 2024)](https://noometry.com/models/gemini-1-5-pro) | [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 75% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 3 | [Gemini 1.5 Pro (May 2024)](https://noometry.com/models/gemini-1-5-pro) | [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 75% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 4 | [Qwen2.5-VL 72B Instruct](https://noometry.com/models/qwen2-5-vl-72b-instruct) | [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 73.5% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 5 | [InternVL2\_5-78B](https://noometry.com/models/internvl2-5-78b) | [![](/logos/shanghai-ai-lab.svg) Shanghai AI Lab](https://noometry.com/providers/shanghai-ai-lab) | 72.1% | 5-78B | [Epoch AI](https://epoch.ai/benchmarks) | | | 6 | [GPT-4o](https://noometry.com/models/gpt-4o) | [OpenAI](https://noometry.com/providers/openai) | 71.9% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 7 | [GPT-4o](https://noometry.com/models/gpt-4o) | [OpenAI](https://noometry.com/providers/openai) | 71.9% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 8 | [Gemini 1.5 Flash (May 2024)](https://noometry.com/models/gemini-1-5-flash) | [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 70.3% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 9 | [GPT-4o mini](https://noometry.com/models/gpt-4o-mini) | [OpenAI](https://noometry.com/providers/openai) | 64.8% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 10 | [NVILA 8B](https://noometry.com/models/nvila-8b) | [![](/logos/nvidia.svg) NVIDIA](https://noometry.com/providers/nvidia) | 64.2% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 11 | [InternVL2-40B](https://noometry.com/models/internvl2-40b) | [![](/logos/shanghai-ai-lab.svg) Shanghai AI Lab](https://noometry.com/providers/shanghai-ai-lab) | 61.2% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 12 | [Claude 3.5 Sonnet](https://noometry.com/models/claude-3-5-sonnet) | [Anthropic](https://noometry.com/providers/anthropic) | 60% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 13 | [Claude 3.5 Sonnet](https://noometry.com/models/claude-3-5-sonnet) | [Anthropic](https://noometry.com/providers/anthropic) | 60% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 14 | [GPT-4V](https://noometry.com/models/gpt-4v) | [OpenAI](https://noometry.com/providers/openai) | 59.9% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 15 | [Qwen-VL Max](https://noometry.com/models/qwen-vl-max) | [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 51.3% | | [Epoch AI](https://epoch.ai/benchmarks) | | ## Compare the leaders - [video-SALMONN 2+ vs Gemini 1.5 Pro (May 2024)](https://noometry.com/compare/gemini-1-5-pro-vs-video-salmonn-2-plus) - [video-SALMONN 2+ vs Gemini 1.5 Pro (May 2024)](https://noometry.com/compare/gemini-1-5-pro-vs-video-salmonn-2-plus) - [video-SALMONN 2+ vs Qwen2.5-VL 72B Instruct](https://noometry.com/compare/qwen2-5-vl-72b-instruct-vs-video-salmonn-2-plus) - [video-SALMONN 2+ vs InternVL2\_5-78B](https://noometry.com/compare/internvl2-5-78b-vs-video-salmonn-2-plus) - [Gemini 1.5 Pro (May 2024) vs Gemini 1.5 Pro (May 2024)](https://noometry.com/compare/gemini-1-5-pro-vs-gemini-1-5-pro) - [Gemini 1.5 Pro (May 2024) vs Qwen2.5-VL 72B Instruct](https://noometry.com/compare/gemini-1-5-pro-vs-qwen2-5-vl-72b-instruct) ## Other multimodal benchmarks - [LMArena Vision](https://noometry.com/benchmarks/arena-vision) - [GeoBench](https://noometry.com/benchmarks/geobench) - [VPCT](https://noometry.com/benchmarks/vpct) - [Blueprint-Bench 2](https://noometry.com/benchmarks/blueprint-bench-2) - [Furniture Assembly](https://noometry.com/benchmarks/furniture-assembly) - [LMArena Document](https://noometry.com/benchmarks/arena-document) (reference) - [MindCube](https://noometry.com/benchmarks/mindcube) (reference) - [ScienceQA](https://noometry.com/benchmarks/scienceqa) (reference) - [SpatialViz-Bench](https://noometry.com/benchmarks/spatialviz-bench) (reference) ## Frequently asked questions ### What does Video-MME measure? Multiple-choice questions about short, medium and long videos. Scores here are without subtitles. ### Which model has the highest Video-MME score? As of October 2026, video-SALMONN 2+ has the highest published Video-MME score on Noometry at 79.7%, out of 15 models with results. ### What is the best open-weight model on Video-MME? Qwen2.5-VL 72B Instruct has the highest Video-MME accuracy among open-weight models at 73.5%, ranking 4 of 15 overall. ### Cite this page Noometry. (2026). Video-MME leaderboard. Retrieved October 10, 2026, from https://noometry.com/benchmarks/video-mme Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/benchmarks/video-mme.md).