LetTokenBurnBenchHub

Model

Qwen-VL-Max

Alibaba · open weights

qwenlm.github.io

Knowledge & Reasoning

Knowledge & Reasoning

Benchmark	Score	Metric	Harness	Source	Confidence	Link
ScienceQA	68.2	score	N/A	Independent	medium	proceedings.neurips.cc

Math

Benchmark	Score	Metric	Harness	Source	Confidence	Link
MATH-V	15.6	accuracy	N/A	Independent	medium	arxiv.org

Multimodal

Benchmark	Score	Metric	Harness	Source	Confidence	Link
ChartQA	66.3	1:1_accuracy	N/A	Independent	medium	arxiv.org
EmbSpatial-Bench	49.1	generation	N/A	Independent	medium	arxiv.org
InfiMM-Eval	37.4	overall_score	N/A	Independent	medium	arxiv.org
MM-Vet	66.6	gpt-4_score	N/A	Independent	medium	arxiv.org
MM-Vet v2	55.8	gpt-4_score	N/A	Independent	medium	arxiv.org
ScreenSpot	5.2	accuracy_(%)	N/A	Independent	medium	arxiv.org
SME	24.3	bleu-4	N/A	Independent	medium	arxiv.org
SpatialViz-Bench	32.0	overall_score	N/A	Independent	medium	arxiv.org
Video-MME	51.3	overall_(no_subtitles)	N/A	Independent	medium	video-mme.github.io
WOVEN	69.6	accuracy	N/A	Independent	medium	arxiv.org

Reproduced by the community