1. Chart data
  2. Qwen
  3. Qwen3-VL vs Other Models
QwenTable chart · 148 points · Qwen-VL and QVQ

Qwen3-VL vs Other Models

The numbers behind a chart Qwen published, redrawn natively. Check the original, study the data, then make your own.

Estimated from the image 50%All Qwen modelsAll chart data
Chart by Qwen. Source: x.com

Simplified redraw

Drawn by us from the numbers below. Hover, tap or use the arrow keys.

A simplified redraw: it shows the numbers in our own look, not the look of the original. One accent marks what the chart is about. Values marked with ~ in the table are estimates.

The numbers

First 10 of 148 points are free
GroupSeriesValue (score)SourceConf.
MMMU_Pro_ValQwen3-VL~76Estimate0.50
MMMU_Pro_fullQwen3-VL~65.7Estimate0.50
MathVista_miniQwen3-VL~81.9Estimate0.50
MathVisionQwen3-VL~79.6Estimate0.50
MMBench_CN_EN_V1.1Qwen3-VL~88.9Estimate0.50
RealWorldQAQwen3-VL~77.4Estimate0.50
SimpleVQAQwen3-VL~54.3Estimate0.50
HallusionBenchQwen3-VL~66Estimate0.50
MM-MT-BenchQwen3-VL~7.9Estimate0.50
DocVQA_testQwen3-VL~95Estimate0.50

Max data, free with your email for now

See all 148 points and download the files

The full table, the JSON, a CSV and the agent skill file for this chart. These are Max in the plan; while this is a prototype your email unlocks them.

Unlocks all 35 giants. One email a week, leave any time. What you get · Log in

InfoVQA_testQwen3-VL~86Estimate0.50
OCRBenchQwen3-VL~839Estimate0.50
OCRBenchV2_fullQwen3-VL~62.6Estimate0.50
CharXivPqQwen3-VL~56.9Estimate0.50
CharXivPqQwen3-VL~56.5Estimate0.50
CountBenchQwen3-VL~90Estimate0.50
OdinW13Qwen3-VL~42.3Estimate0.50
ARKISGSceneQwen3-VL~55.6Estimate0.50
BLINKQwen3-VL~65.4Estimate0.50
MURBENCHQwen3-VL~77.6Estimate0.50
ERQAQwen3-VL~45.3Estimate0.50
EmbSpatialBenchQwen3-VL~80.6Estimate0.50
RefSpatialBenchQwen3-VL~54.2Estimate0.50
RobSpatialHomeQwen3-VL~65.5Estimate0.50
MVBenchQwen3-VL~72Estimate0.50
VideoMMEQwen3-VL~73.3Estimate0.50
MVU3.0Qwen3-VL~62.7Estimate0.50
LVBenchQwen3-VL~59.2Estimate0.50
CharadesSTAQwen3-VL~75Estimate0.50
VideoMMUQwen3-VL~94.7Estimate0.50
ScreenSpotQwen3-VL~57.3Estimate0.50
ScreenSpot ProQwen3-VL~59.6Estimate0.50
AndroidWorldQwen3-VL~55Estimate0.50
OSWorldQwen3-VL~30.6Estimate0.50
V*Qwen3-VL~81.2Estimate0.50
HRBench4KQwen3-VL~77.8Estimate0.50
HRBench8KQwen3-VL~74.4Estimate0.50
MMMU_Pro_ValGPT5-Mini~79Estimate0.50
MMMU_Pro_fullGPT5-Mini~67.3Estimate0.50
MathVista_miniGPT5-Mini~71.9Estimate0.50
MathVisionGPT5-Mini~78.8Estimate0.50
MMBench_CN_EN_V1.1GPT5-Mini~86.8Estimate0.50
RealWorldQAGPT5-Mini~79Estimate0.50
SimpleVQAGPT5-Mini~56.8Estimate0.50
HallusionBenchGPT5-Mini~63.2Estimate0.50
MM-MT-BenchGPT5-Mini~7.7Estimate0.50
DocVQA_testGPT5-Mini~92Estimate0.50
InfoVQA_testGPT5-Mini~78Estimate0.50
OCRBenchGPT5-Mini~821Estimate0.50
OCRBenchV2_fullGPT5-Mini~52.6Estimate0.50
CharXivPqGPT5-Mini~45.1Estimate0.50
CharXivPqGPT5-Mini~45.1Estimate0.50
CountBenchGPT5-Mini~91Estimate0.50
OdinW13GPT5-Mini~45Estimate0.50
ARKISGSceneGPT5-Mini~45Estimate0.50
BLINKGPT5-Mini~54Estimate0.50
MURBENCHGPT5-Mini~46Estimate0.50
ERQAGPT5-Mini~30.7Estimate0.50
EmbSpatialBenchGPT5-Mini~80.7Estimate0.50
RefSpatialBenchGPT5-Mini~9Estimate0.50
RobSpatialHomeGPT5-Mini~54.3Estimate0.50
MVBenchGPT5-Mini~78.9Estimate0.50
VideoMMEGPT5-Mini~83.3Estimate0.50
MVU3.0GPT5-Mini~68.8Estimate0.50
LVBenchGPT5-Mini~82.5Estimate0.50
CharadesSTAGPT5-Mini~72.7Estimate0.50
VideoMMUGPT5-Mini~78.6Estimate0.50
ScreenSpotGPT5-Mini~78.6Estimate0.50
ScreenSpot ProGPT5-Mini~78.6Estimate0.50
AndroidWorldGPT5-Mini~45Estimate0.50
OSWorldGPT5-Mini~45Estimate0.50
V*GPT5-Mini~78.6Estimate0.50
HRBench4KGPT5-Mini~78.6Estimate0.50
HRBench8KGPT5-Mini~49.8Estimate0.50
MMMU_Pro_ValClaude3.4-Sonnet~74.4Estimate0.50
MMMU_Pro_fullClaude3.4-Sonnet~61.6Estimate0.50
MathVista_miniClaude3.4-Sonnet~74.6Estimate0.50
MathVisionClaude3.4-Sonnet~68.6Estimate0.50
MMBench_CN_EN_V1.1Claude3.4-Sonnet~82.2Estimate0.50
RealWorldQAClaude3.4-Sonnet~69.8Estimate0.50
SimpleVQAClaude3.4-Sonnet~53.3Estimate0.50
HallusionBenchClaude3.4-Sonnet~59.2Estimate0.50
MM-MT-BenchClaude3.4-Sonnet~7.9Estimate0.50
DocVQA_testClaude3.4-Sonnet~90.4Estimate0.50
InfoVQA_testClaude3.4-Sonnet~58Estimate0.50
OCRBenchClaude3.4-Sonnet~739Estimate0.50
OCRBenchV2_fullClaude3.4-Sonnet~44.9Estimate0.50
CharXivPqClaude3.4-Sonnet~39.4Estimate0.50
CharXivPqClaude3.4-Sonnet~39.4Estimate0.50
CountBenchClaude3.4-Sonnet~91Estimate0.50
OdinW13Claude3.4-Sonnet~45Estimate0.50
ARKISGSceneClaude3.4-Sonnet~45Estimate0.50
BLINKClaude3.4-Sonnet~60.4Estimate0.50
MURBENCHClaude3.4-Sonnet~68.6Estimate0.50
ERQAClaude3.4-Sonnet~33.3Estimate0.50
EmbSpatialBenchClaude3.4-Sonnet~68.5Estimate0.50
RefSpatialBenchClaude3.4-Sonnet~3.6Estimate0.50
RobSpatialHomeClaude3.4-Sonnet~69.7Estimate0.50
MVBenchClaude3.4-Sonnet~72.3Estimate0.50
VideoMMEClaude3.4-Sonnet~68.8Estimate0.50
MVU3.0Claude3.4-Sonnet~68.8Estimate0.50
LVBenchClaude3.4-Sonnet~72.7Estimate0.50
CharadesSTAClaude3.4-Sonnet~72.7Estimate0.50
VideoMMUClaude3.4-Sonnet~78.6Estimate0.50
ScreenSpotClaude3.4-Sonnet~78.6Estimate0.50
ScreenSpot ProClaude3.4-Sonnet~78.6Estimate0.50
AndroidWorldClaude3.4-Sonnet~45Estimate0.50
OSWorldClaude3.4-Sonnet~45Estimate0.50
V*Claude3.4-Sonnet~45Estimate0.50
HRBench4KClaude3.4-Sonnet~58.5Estimate0.50
HRBench8KClaude3.4-Sonnet~49.8Estimate0.50
MMMU_Pro_ValOther Best~75.6Estimate0.50
MMMU_Pro_fullOther Best~57.1Estimate0.50
MathVista_miniOther Best~81.8Estimate0.50
MathVisionOther Best~85.8Estimate0.50
MMBench_CN_EN_V1.1Other Best~72.3Estimate0.50
RealWorldQAOther Best~53.8Estimate0.50
SimpleVQAOther Best~53.8Estimate0.50
HallusionBenchOther Best~95.7Estimate0.50
MM-MT-BenchOther Best~88Estimate0.50
DocVQA_testOther Best~95.7Estimate0.50
InfoVQA_testOther Best~87.9Estimate0.50
OCRBenchOther Best~880Estimate0.50
OCRBenchV2_fullOther Best~87Estimate0.50
CharXivPqOther Best~56.5Estimate0.50
CharXivPqOther Best~56.5Estimate0.50
CountBenchOther Best~65.1Estimate0.50
OdinW13Other Best~65.1Estimate0.50
ARKISGSceneOther Best~74.7Estimate0.50
BLINKOther Best~63.7Estimate0.50
MURBENCHOther Best~78.6Estimate0.50
ERQAOther Best~54Estimate0.50
EmbSpatialBenchOther Best~72.4Estimate0.50
RefSpatialBenchOther Best~72.1Estimate0.50
RobSpatialHomeOther Best~68.7Estimate0.50
MVBenchOther Best~73Estimate0.50
VideoMMEOther Best~61Estimate0.50
MVU3.0Other Best~50Estimate0.50
LVBenchOther Best~81.7Estimate0.50
CharadesSTAOther Best~41.7Estimate0.50
VideoMMUOther Best~56.1Estimate0.50
ScreenSpotOther Best~52.8Estimate0.50
ScreenSpot ProOther Best~14.9Estimate0.50
AndroidWorldOther Best~81.7Estimate0.50
OSWorldOther Best~81.7Estimate0.50
V*Other Best~81.7Estimate0.50
HRBench4KOther Best~81.7Estimate0.50
HRBench8KOther Best~81.7Estimate0.50
Download this chart's data

Max subscribers get the same data by API. API docs

API · Max

Use this chart via API

On the Max plan you can pull this chart's numbers with the provenance of each one, as JSON or CSV, with its redraw spec, or call it from an agent over MCP. Chart id dfc55ea55247.

PathReturnsPlan
GET/api/v1/charts/dfc55ea55247Title, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/dfc55ea55247/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/dfc55ea55247/render?view=1The draw-only view this page usesOpen
POST/mcpTool get_chart_data with this id, for Claude, Cursor and other agentsMax
curlMax
curl -s https://viral-chart.com/api/v1/charts/dfc55ea55247/data \
  -H "Authorization: Bearer $VIRALCHART_KEY"
Claude CodeMax
claude mcp add --transport http viralchart https://viral-chart.com/mcp \
  --header "Authorization: Bearer $VIRALCHART_KEY"

60 requests a minute per key; over that you get 429 with Retry-After. Up to 5 keys per account, made on your account page and shown once. Without Max, the data route answers 402 with a link to the plans. The numbers describe a chart its publisher owns, and every file carries a license note.

Make one like this

This chart's shape, your numbers.

Live preview. Everything stays on your device.

Pick the form

A simplified form: our own look, not the look of the original. Your numbers start from this chart's data.

More data from Qwen

All chart data

Questions people ask

How accurate are these numbers?

They are estimated from the image by two independent passes, with confidence 0.50 on a 0 to 1 scale. Printed numbers read well; values read off an axis can be a few percent off.

Can I reuse this data?

The numbers describe a chart that Qwen published. The image, layout and styling belong to them. Use the numbers with a credit to the publisher, and make your picture from your own data.

How do I get the file?

The JSON, CSV and agent skill file are under the email gate on this page. In this prototype they are static files at /api/charts/dfc55ea55247.json and /api/charts/dfc55ea55247.skill.md.