Skip to content

Benchmark

Video-MME

Vision benchmarks measure how well models understand images. Scores are percentages. Higher is better.

Models measured
35
Scores recorded
44
Sources
3
IQ weight
2.35

Score distribution

62%
Mean
83.7%
Median
36.1%
Std dev
0.639%
10th percentile
88%
90th percentile
0.513%
Min
0.513%90.4%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.35 for chat models, measured over 33 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Qwen3.8 MaxQwen3.8-Max release vision/video table · subtitles enabled· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.90.4%
2Kimi K3with subtitles · three-run average · max effort · temp 1.0 · top_p .95· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.90%
3Doubao Seed 2.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim89.2%
4Doubao Seed 2.1 Turbo· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim89%
5Qwen3.7 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim88%
6Qwen3.7 PlusQwen3.7-Plus release · subtitles enabled· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.88%
7Qwen3.6 PlusQwen official release table · thinking mode unless benchmark requires otherwise · with subtitles· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.87.8%
8MiMo V2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim87.7%
9MiMo V2.5Xiaomi MiMo-V2.5 official release/model card · subtitle/audio setting unspecified· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.87.7%
10Qwen3.6 27BQwen official release table · thinking mode unless benchmark requires otherwise · with subtitles· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.87.7%
11Qwen3.5 397B A17BQwen3.5 release/model card · with subtitles· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.87.5%
12Kimi K2.5setting not named by the source· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.87.4%
13Kimi K2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim87.4%
14Qwen3.6 FlashQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · with subtitles· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.86.6%
15MiniMax M3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim85.4%
16MiniMax M3with subtitles · 1 FPS · ≤1024 frames· Reported by MiniMax Research· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.85.4%
17MiMo V2 OmniXiaomi MiMo-V2-Omni release table · native audio-video input · exact benchmark version unspecified· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.85.3%
18LongCat 2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim85.2%
19Gemini 2.5 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim84.8%
20Qwen3.6 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim84.2%
21Qwen3.6 PlusQwen official release table · thinking mode unless benchmark requires otherwise · without subtitles· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.84.2%
22Qwen3.5 397B A17BQwen3.5 release/model card · without subtitles· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.83.7%
23Qwen3.6 FlashQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · without subtitles· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.82.5%
24Qwen3.5 Omni PlusQwen3.5-Omni release · published setting· Reported by Qwen, Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.81.9%
25Gemini 1.5 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78.6%
26Qwen3.5 Omni FlashQwen3.5-Omni release · published setting· Reported by Qwen, Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.77%
27Gemini 1.5 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim76.1%
28gemini-1.5-pro-001· Epoch AI Benchmarking Hub data75%
29qwen3-vl-30b· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.74.5%
30Qwen2.5 VL 72B Instruct· Epoch AI Benchmarking Hub data73.5%
31qwen3-vl-30bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.73.3%
32GPT 4o· Epoch AI Benchmarking Hub data71.9%
33Qwen: Qwen3 VL 8B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.71.8%
34Qwen3 VL 8B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.71.4%
35Qwen2-VL (72B) Instruct· Epoch AI Benchmarking Hub data71.2%
36gemini-1.5-flash-001· Epoch AI Benchmarking Hub data70.3%
37Gemini 1.5 Flash-8B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim66.2%
38GPT-4o mini· Epoch AI Benchmarking Hub data64.8%
39Qwen2 VL 7b Instruct· Epoch AI Benchmarking Hub data63.9%
40MiniCPM-V 2.6· Epoch AI Benchmarking Hub data60.9%
41Claude 3.5 Sonnet· Epoch AI Benchmarking Hub data60%
42GPT-4-1106-vision-preview· Epoch AI Benchmarking Hub data59.9%
43Phi 4 Multimodal Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim55%
44Qwen-VL Max· Epoch AI Benchmarking Hub data51.3%

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Data by LLM Stats · BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.