Video-MME with subtitle

A video understanding benchmark that allows subtitle access when answering multimodal questions about videos.

ModelsModels with a result.12
Top resultBest result on this benchmark.—
Top-3 spreadPoints from first to third.—
YearYear of release.—

Result and price

10 of 12 results

Results

12 results
#ModelResultThe score from the source.
—Qwen3.8 Max90.4%
—Gemini 3 Pro88.4%
—Qwen3.7 Plus88.0%
—MiMo-V2.587.7%
—Qwen3.6-27B87.7%
—Qwen3.5 397B87.5%
—Kimi K2.587.4%
—GPT-5.286.0%
—MiniMax M385.4%
—LFM3-VL-2B69.0%