MiniMax-VL-01

Home/Models/MiniMaxAI/MiniMax-VL-01

MiniMaxAI/MiniMax-VL-01

kind: original
quant: bf16 (16-bit)
family: minimax
modality: image-text-to-text
root model: MiniMaxAI/MiniMax-VL-01
provider: MiniMaxAI
license: —
language: —
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 10,197
likes: 285
created: —
last modified: 2025-07-03T05:11:03+00:00 (2025)
huggingface: https://huggingface.co/MiniMaxAI/MiniMax-VL-01
tags: safetensorsminimax_vl_01image-text-to-textconversationalcustom_codearxiv:2501.08313region:us

benchmark	category	score	context	conf	evidence
DocVQA	multimodal	91.1	DocVQA<sup>*</sup>	medium	`\| DocVQA<sup></sup> \| 91.1 \| 94.2 \| 91.5 \| 92.9 \| 97.1* \| 96.1 \| 90.1 \| 96.4 \|`
ChartQA	multimodal	88.1	ChartQA<sup>*</sup><sub>relaxed</sub>	medium	`\| ChartQA<sup></sup><sub>relaxed</sub> \| 88.1 \| 90.8 \| 88.7 \| 88.3 \| 91.2 \| 91.5 \| 85.5 \| 91.7* \|`
MMMU	multimodal	63.5	MMMU<sup>*</sup>	medium	`\| MMMU<sup></sup> \| 63.5 \| 72.0* \| 68.4 \| 70.6 \| 64.5 \| 66.5 \| 62.1 \| 68.5 \|`
MathVista	multimodal	62.1	MathVista<sup>*</sup>	medium	`\| MathVista<sup></sup> \| 62.1 \| 65.4 \| 70.6 \| 73.1* \| 69.6 \| 68.4 \| 57.3 \| 68.6 \|`
MMMU	multimodal	54.5	MMMU-Pro<sup>*</sup>	medium	`\| MMMU-Pro<sup></sup> \| 54.5 \| 54.7 \| 50.9 \| 57.0* \| 43.2 \| 47.3 \| 36.0 \| 52.7 \|`
Math Olympiad	math	25.2	OlympiadBench<sub>full</sub>	medium	`\| OlympiadBench<sub>full</sub> \| 25.2 \| 28.4 \| 32.1 \| 46.1 \| 21.9 \| 25.1 \| 19.3 \| 24.2 \|`

none scraped.