1. Chart data
  2. Meta
  3. Model Benchmark Comparison
MetaTable chart · 98 points · Muse Glimmer

Model Benchmark Comparison

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

Estimated from the image 57%All Meta modelsAll chart data
Chart by Meta. Source: x.com

Our replica

Look-alike score 7.9 of 10
The original, Meta
Our replica. Look-alike score 7.9 of 10Swipe sideways to read the labels.

Drawn by us in your browser from the numbers below, in the same layout, palette and label style as the original. Values marked with ~ in the table are estimates. A replica needs 7 of 10 from our judges to be shown.

The numbers

First 10 of 98 points are free
GroupSeriesValueSourceConf.
MCP AtlasMuse Glimmer-3B (Thinking High)75.5Estimate0.50
MCP AtlasGemma3-31B (Thinking Mode)54.2Estimate0.50
MCP AtlasQwen3.6-27B (Thinking Mode)62.5Estimate0.97
Deep3-BankingMuse Glimmer-3B (Thinking High)74.6Estimate0.50
Deep3-BankingGemma3-31B (Thinking Mode)61.7Estimate0.50
Deep3-BankingQwen3.6-27B (Thinking Mode)71.1Estimate0.50
GDPval-AAMuse Glimmer-3B (Thinking High)95.3Estimate0.50
GDPval-AAGemma3-31B (Thinking Mode)81.1Estimate0.50
GDPval-AAQwen3.6-27B (Thinking Mode)114.1Estimate0.97
SkillsBench (With Skills)Muse Glimmer-3B (Thinking High)44.3Estimate0.50

Max data, free with your email for now

See all 98 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

SkillsBench (With Skills)Gemma3-31B (Thinking Mode)32.4Estimate0.50
SkillsBench (With Skills)Qwen3.6-27B (Thinking Mode)40Estimate0.30
OSWorld-VerifiedMuse Glimmer-3B (Thinking High)65.9Estimate0.50
OSWorld-VerifiedGemma3-31B (Thinking Mode)58.5Estimate0.50
OSWorld-VerifiedQwen3.6-27B (Thinking Mode)75.6Estimate0.97
SWE-Bench ProMuse Glimmer-3B (Thinking High)51.2Estimate0.50
SWE-Bench ProGemma3-31B (Thinking Mode)36.9Estimate0.50
SWE-Bench ProQwen3.6-27B (Thinking Mode)50.2Estimate0.97
SWE-Bench VerifiedMuse Glimmer-3B (Thinking High)76Estimate0.50
SWE-Bench VerifiedGemma3-31B (Thinking Mode)66.6Estimate0.50
SWE-Bench VerifiedQwen3.6-27B (Thinking Mode)77.2Estimate0.97
TerminalBench 2.1Muse Glimmer-3B (Thinking High)51.7Estimate0.50
TerminalBench 2.1Gemma3-31B (Thinking Mode)43.4Estimate0.50
TerminalBench 2.1Qwen3.6-27B (Thinking Mode)60.7Estimate0.97
SciCodeMuse Glimmer-3B (Thinking High)43.6Estimate0.50
SciCodeGemma3-31B (Thinking Mode)43.4Estimate0.50
SciCodeQwen3.6-27B (Thinking Mode)39.8Estimate0.97
Charxiv ReasoningMuse Glimmer-3B (Thinking High)78.8Estimate0.50
Charxiv ReasoningGemma3-31B (Thinking Mode)77.7Estimate0.50
Charxiv ReasoningQwen3.6-27B (Thinking Mode)78.4Estimate0.97
ScreenSpot ProMuse Glimmer-3B (Thinking High)75.4Estimate0.50
ScreenSpot ProGemma3-31B (Thinking Mode)75.9Estimate0.50
ScreenSpot ProQwen3.6-27B (Thinking Mode)76.1Estimate0.97
OmniDocBench v1.5Muse Glimmer-3B (Thinking High)75.8Estimate0.50
OmniDocBench v1.5Gemma3-31B (Thinking Mode)72.5Estimate0.50
OmniDocBench v1.5Qwen3.6-27B (Thinking Mode)76.95Estimate0.90
MMMU ProMuse Glimmer-3B (Thinking High)74Estimate0.50
MMMU ProGemma3-31B (Thinking Mode)73Estimate0.50
MMMU ProQwen3.6-27B (Thinking Mode)75Estimate0.97
IFBenchMuse Glimmer-3B (Thinking High)77Estimate0.50
IFBenchGemma3-31B (Thinking Mode)76Estimate0.50
IFBenchQwen3.6-27B (Thinking Mode)70.8Estimate0.50
AIME 2026Muse Glimmer-3B (Thinking High)94.7Estimate0.50
AIME 2026Gemma3-31B (Thinking Mode)89.2Estimate0.50
AIME 2026Qwen3.6-27B (Thinking Mode)94.1Estimate0.97
GPQA DiamondMuse Glimmer-3B (Thinking High)83.5Estimate0.50
GPQA DiamondGemma3-31B (Thinking Mode)85.7Estimate0.50
GPQA DiamondQwen3.6-27B (Thinking Mode)84.2Estimate0.97
Humanity's Last Exam (Text-No Tools)Muse Glimmer-3B (Thinking High)22Estimate0.50
Humanity's Last Exam (Text-No Tools)Gemma3-31B (Thinking Mode)23.6Estimate0.50
Humanity's Last Exam (Text-No Tools)Qwen3.6-27B (Thinking Mode)23.1Estimate0.97
AA-LCRMuse Glimmer-3B (Thinking High)80Estimate0.50
AA-LCRGemma3-31B (Thinking Mode)68.3Estimate0.50
AA-LCRQwen3.6-27B (Thinking Mode)73.3Estimate0.97
MCP AtlasMuse Glimmer-30B75.5Estimate0.50
DeepResearch QAMuse Glimmer-30B74.6Estimate0.50
τ²-BankingMuse Glimmer-30B23.5Estimate0.50
GDPval-AAMuse Glimmer-30B95.3Estimate0.50
GAIA2Muse Glimmer-30B43.3Estimate0.50
SkillsBenchMuse Glimmer-30B44.3Estimate0.50
OSWorld-VerifiedMuse Glimmer-30B65.9Estimate0.50
SWE-Bench ProMuse Glimmer-30B51.2Estimate0.50
SWE-Bench VerifiedMuse Glimmer-30B76Estimate0.50
TerminalBench 2.1Muse Glimmer-30B51.7Estimate0.50
SciCodeMuse Glimmer-30B43.6Estimate0.50
Charxiv ReasoningMuse Glimmer-30B78.8Estimate0.50
ScreenSpot ProMuse Glimmer-30B75.4Estimate0.50
OmniDocBench v1.5Muse Glimmer-30B75.8Estimate0.50
MMMU ProMuse Glimmer-30B74Estimate0.50
AIME 2026Muse Glimmer-30B94.7Estimate0.50
GPQA DiamondMuse Glimmer-30B83.5Estimate0.50
Humanity's Last ExamMuse Glimmer-30B22Estimate0.50
AA-LCRMuse Glimmer-30B80Estimate0.50
Beam 128KMuse Glimmer-30B65.1Estimate0.50
MCP AtlasGemma4-31B54.2Estimate0.50
DeepResearch QAGemma4-31B61.7Estimate0.50
τ²-BankingGemma4-31B15.1Estimate0.50
GDPval-AAGemma4-31B81.1Estimate0.50
GAIA2Gemma4-31B36.4Estimate0.50
SkillsBenchGemma4-31B32.4Estimate0.50
OSWorld-VerifiedGemma4-31B58.5Estimate0.50
SWE-Bench ProGemma4-31B36.9Estimate0.50
SWE-Bench VerifiedGemma4-31B66.6Estimate0.50
TerminalBench 2.1Gemma4-31B43.4Estimate0.50
SciCodeGemma4-31B43.4Estimate0.50
Charxiv ReasoningGemma4-31B77.7Estimate0.50
ScreenSpot ProGemma4-31B75.9Estimate0.50
OmniDocBench v1.5Gemma4-31B73Estimate0.50
MMMU ProGemma4-31B73Estimate0.50
AIME 2026Gemma4-31B89.2Estimate0.50
GPQA DiamondGemma4-31B85.7Estimate0.50
Humanity's Last ExamGemma4-31B23.6Estimate0.50
AA-LCRGemma4-31B68.3Estimate0.50
Beam 128KGemma4-31B58.2Estimate0.50
DeepResearch QAQwen3.6-27B71.1Estimate0.50
τ²-BankingQwen3.6-27B16.7Estimate0.50
GAIA2Qwen3.6-27B40Estimate0.50
Beam 128KQwen3.6-27B63Estimate0.50
Download this chart's data

Max subscribers get the same data by API. API docs

JSONAgent skill file

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 b62b4efec99b.

See the Max planAPI docs
PathReturnsPlan
GET/api/v1/charts/b62b4efec99bTitle, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/b62b4efec99b/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/b62b4efec99b/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/b62b4efec99b/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

Start from our replica of this chart, or from a simplified form. Either way your numbers start from this chart's real data.

More data from Meta

All chart data
Estimated from the imageReplica 8.3Llama3.1 405B Human EvaluationMeta · Stacked bar chart · 9 pointsEstimated from the imageReplica 8.1AI Model Performance TrendMeta · Line chart · 4 pointsEstimated from the imageTerminal-Bench 2.1, DeepSWE 1.1, Meta Internal Coding BenchMeta · Benchmark bar chart · 17 pointsEstimated from the imageGoogle and Meta are Benchmaxxerssemianalysis · Table chart · 12 pointsEstimated from the imageBenchmark ComparisonMeta · Table chart · 13 pointsEstimated from the imageMCP Atlas vs GDPval-AA V2Meta · Benchmark bar chart · 14 points

Questions people ask

How accurate are these numbers?

They are estimated from the image by two independent passes, with confidence 0.57 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 Meta 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/b62b4efec99b.json and /api/charts/b62b4efec99b.skill.md.