1. Chart data
  2. Qwen
  3. Model Benchmarks Comparison
QwenTable chart · 223 points · Qwen3

Model Benchmarks Comparison

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

Estimated from the image 50%Qwen3All 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 223 points are free
GroupSeriesValue (score)SourceConf.
Coding AgentSWE-bench Verified75Estimate0.50
Coding AgentSWE-bench Verified76.2Estimate0.50
Coding AgentSWE-bench Verified52Estimate0.50
Coding AgentSWE-bench Verified80.9Estimate0.50
Coding AgentSWE-bench Verified73.4Estimate0.50
Coding AgentSWE-bench Verified77.2Estimate0.50
Coding AgentSWE-bench Multilingual69.3Estimate0.50
Coding AgentSWE-bench Multilingual69.3Estimate0.50
Coding AgentSWE-bench Multilingual35.7Estimate0.50
Coding AgentSWE-bench Multilingual51.7Estimate0.50

Max data, free with your email for now

See all 223 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

Coding AgentSWE-bench Multilingual77.5Estimate0.50
Coding AgentSWE-bench Multilingual67.2Estimate0.50
Coding AgentSWE-bench Multilingual53.5Estimate0.50
Coding AgentSWE-bench Terminal-Bench 2.041.6Estimate0.50
Coding AgentSWE-bench Terminal-Bench 2.030Estimate0.50
Coding AgentSWE-bench Terminal-Bench 2.042.9Estimate0.50
Coding AgentSWE-bench Terminal-Bench 2.059.3Estimate0.50
Coding AgentSWE-bench Terminal-Bench 2.051.5Estimate0.50
Coding AgentSWE-bench Terminal-Bench 2.059.3Estimate0.50
Coding AgentQwenWebBench Avg27.2Estimate0.50
Coding AgentQwenWebBench Avg30Estimate0.50
Coding AgentQwenWebBench Avg23.6Estimate0.50
Coding AgentQwenWebBench Avg45.3Estimate0.50
Coding AgentQwenWebBench Avg28.7Estimate0.50
Coding AgentQwenWebBench Avg48.2Estimate0.50
Coding AgentNL2Repo27.3Estimate0.50
Coding AgentNL2Repo32.2Estimate0.50
Coding AgentNL2Repo19.5Estimate0.50
Coding AgentNL2Repo43.2Estimate0.50
Coding AgentNL2Repo29.4Estimate0.50
Coding AgentNL2Repo36.2Estimate0.50
Coding AgentClaw-Eval Avg64.3Estimate0.50
Coding AgentClaw-Eval Avg70.7Estimate0.50
Coding AgentClaw-Eval Avg48.5Estimate0.50
Coding AgentClaw-Eval Avg76.6Estimate0.50
Coding AgentClaw-Eval Avg68.7Estimate0.50
Coding AgentClaw-Eval Avg72.4Estimate0.50
Coding AgentQwenClawBench52.2Estimate0.50
Coding AgentQwenClawBench51.8Estimate0.50
Coding AgentQwenClawBench41.7Estimate0.50
Coding AgentQwenClawBench52.3Estimate0.50
Coding AgentQwenClawBench52.6Estimate0.50
Coding AgentQwenClawBench53.4Estimate0.50
KnowledgeMMLU-Pro86.1Estimate0.50
KnowledgeMMLU-Pro87.8Estimate0.50
KnowledgeMMLU-Pro85.2Estimate0.50
KnowledgeMMLU-Pro89.5Estimate0.50
KnowledgeMMLU-Pro85.2Estimate0.50
KnowledgeMMLU-Pro86.2Estimate0.50
KnowledgeMMLU-Redux93.2Estimate0.50
KnowledgeMMLU-Redux94.9Estimate0.50
KnowledgeMMLU-Redux93.7Estimate0.50
KnowledgeMMLU-Redux95.6Estimate0.50
KnowledgeMMLU-Redux93.3Estimate0.50
KnowledgeMMLU-Redux93.5Estimate0.50
KnowledgeSuperGPQA65.6Estimate0.50
KnowledgeSuperGPQA70.4Estimate0.50
KnowledgeSuperGPQA65.7Estimate0.50
KnowledgeSuperGPQA70.6Estimate0.50
KnowledgeSuperGPQA64.7Estimate0.50
KnowledgeSuperGPQA66Estimate0.50
STEM & ReasoningC-Eval Diamond90.5Estimate0.50
STEM & ReasoningC-Eval Diamond93Estimate0.50
STEM & ReasoningC-Eval Diamond82.6Estimate0.50
STEM & ReasoningC-Eval Diamond92.2Estimate0.50
STEM & ReasoningC-Eval Diamond90Estimate0.50
STEM & ReasoningC-Eval Diamond91.4Estimate0.50
STEM & ReasoningGPQA Diamond85.5Estimate0.50
STEM & ReasoningGPQA Diamond88.4Estimate0.50
STEM & ReasoningGPQA Diamond84.3Estimate0.50
STEM & ReasoningGPQA Diamond87Estimate0.50
STEM & ReasoningGPQA Diamond86Estimate0.50
STEM & ReasoningGPQA Diamond87.8Estimate0.50
STEM & ReasoningLiveCodeBench v680.7Estimate0.50
STEM & ReasoningLiveCodeBench v683.6Estimate0.50
STEM & ReasoningLiveCodeBench v680Estimate0.50
STEM & ReasoningLiveCodeBench v684.8Estimate0.50
STEM & ReasoningLiveCodeBench v680.4Estimate0.50
STEM & ReasoningLiveCodeBench v683.9Estimate0.50
STEM & ReasoningHLE24.3Estimate0.50
STEM & ReasoningHLE28.7Estimate0.50
STEM & ReasoningHLE19.5Estimate0.50
STEM & ReasoningHLE30.8Estimate0.50
STEM & ReasoningHLE21.4Estimate0.50
STEM & ReasoningHLE24Estimate0.50
STEM & ReasoningHMMT Feb 2592Estimate0.50
STEM & ReasoningHMMT Feb 2594.8Estimate0.50
STEM & ReasoningHMMT Feb 2588.7Estimate0.50
STEM & ReasoningHMMT Feb 2592.9Estimate0.50
STEM & ReasoningHMMT Feb 2590.7Estimate0.50
STEM & ReasoningHMMT Feb 2593.8Estimate0.50
STEM & ReasoningHMMT Feb 2684.3Estimate0.50
STEM & ReasoningHMMT Feb 2687.9Estimate0.50
STEM & ReasoningHMMT Feb 2677.2Estimate0.50
STEM & ReasoningHMMT Feb 2685.3Estimate0.50
STEM & ReasoningHMMT Feb 2683.6Estimate0.50
STEM & ReasoningHMMT Feb 2684.3Estimate0.50
STEM & ReasoningIMOAnswerBench79.9Estimate0.50
STEM & ReasoningIMOAnswerBench80.9Estimate0.50
STEM & ReasoningIMOAnswerBench74.5Estimate0.50
STEM & ReasoningIMOAnswerBench84Estimate0.50
STEM & ReasoningIMOAnswerBench78.9Estimate0.50
STEM & ReasoningIMOAnswerBench80.8Estimate0.50
STEM & ReasoningAIME2692.6Estimate0.50
STEM & ReasoningAIME2693.3Estimate0.50
STEM & ReasoningAIME2689.2Estimate0.50
STEM & ReasoningAIME2695.1Estimate0.50
STEM & ReasoningAIME2692.7Estimate0.50
STEM & ReasoningAIME2694.1Estimate0.50
Qwen3.5-27BSWE-bench Verified75Estimate0.50
Qwen3.5-27BSWE-bench Multilingual69.3Estimate0.50
Qwen3.5-27BSWE-bench Terminal-Bench 2.041.6Estimate0.50
Qwen3.5-27BQwenWebBench1068Estimate0.50
Qwen3.5-27BSkillsBench27.2Estimate0.50
Qwen3.5-27BNL2Repo27.3Estimate0.50
Qwen3.5-27BClaw-Eval Avg64.3Estimate0.50
Qwen3.5-27BClaw-Eval Pass-346.2Estimate0.50
Qwen3.5-27BQwenClawBench52.2Estimate0.50
Qwen3.5-27BMMLU-Pro86.1Estimate0.50
Qwen3.5-27BMMLU-Redux93.2Estimate0.50
Qwen3.5-27BSuperGPQA65.6Estimate0.50
Qwen3.5-27BC-Eval90.5Estimate0.50
Qwen3.5-27BGPQA Diamond85.5Estimate0.50
Qwen3.5-27BLiveCodeBench v624.3Estimate0.50
Qwen3.5-27BHMMT Feb 2592Estimate0.50
Qwen3.5-27BHMMT Feb 2684.3Estimate0.50
Qwen3.5-27BIMOAnswerBench79.9Estimate0.50
Qwen3.5-27BAIME2692.6Estimate0.50
Qwen3.5-397B-A17BSWE-bench Verified76.2Estimate0.50
Qwen3.5-397B-A17BSWE-bench Multilingual69.3Estimate0.50
Qwen3.5-397B-A17BSWE-bench Terminal-Bench 2.027.2Estimate0.50
Qwen3.5-397B-A17BQwenWebBench30Estimate0.50
Qwen3.5-397B-A17BSkillsBench32Estimate0.50
Qwen3.5-397B-A17BNL2Repo32.2Estimate0.50
Qwen3.5-397B-A17BClaw-Eval Avg70.7Estimate0.50
Qwen3.5-397B-A17BClaw-Eval Pass-348.1Estimate0.50
Qwen3.5-397B-A17BQwenClawBench51.8Estimate0.50
Qwen3.5-397B-A17BMMLU-Pro87.8Estimate0.50
Qwen3.5-397B-A17BMMLU-Redux94.9Estimate0.50
Qwen3.5-397B-A17BSuperGPQA70.4Estimate0.50
Qwen3.5-397B-A17BC-Eval93Estimate0.50
Qwen3.5-397B-A17BGPQA Diamond88.4Estimate0.50
Qwen3.5-397B-A17BLiveCodeBench v628.7Estimate0.50
Qwen3.5-397B-A17BHMMT Feb 2594.8Estimate0.50
Qwen3.5-397B-A17BHMMT Feb 2689.8Estimate0.50
Qwen3.5-397B-A17BIMOAnswerBench80.9Estimate0.50
Qwen3.5-397B-A17BAIME2693.3Estimate0.50
Gemma4-32BSWE-bench Verified52Estimate0.50
Gemma4-32BSWE-bench Multilingual35.7Estimate0.50
Gemma4-32BSWE-bench Terminal-Bench 2.042.9Estimate0.50
Gemma4-32BQwenWebBench1186Estimate0.50
Gemma4-32BSkillsBench15.5Estimate0.50
Gemma4-32BNL2Repo15.5Estimate0.50
Gemma4-32BClaw-Eval Avg48.5Estimate0.50
Gemma4-32BClaw-Eval Pass-325Estimate0.50
Gemma4-32BQwenClawBench41.7Estimate0.50
Gemma4-32BMMLU-Pro85.2Estimate0.50
Gemma4-32BMMLU-Redux93.7Estimate0.50
Gemma4-32BSuperGPQA65.7Estimate0.50
Gemma4-32BC-Eval82.6Estimate0.50
Gemma4-32BGPQA Diamond84.3Estimate0.50
Gemma4-32BLiveCodeBench v680Estimate0.50
Gemma4-32BHMMT Feb 2588.7Estimate0.50
Gemma4-32BHMMT Feb 2687.5Estimate0.50
Gemma4-32BIMOAnswerBench74.5Estimate0.50
Gemma4-32BAIME2689.2Estimate0.50
Claude 4.5 OpusSWE-bench Verified80.9Estimate0.50
Claude 4.5 OpusSWE-bench Multilingual51.7Estimate0.50
Claude 4.5 OpusSWE-bench Terminal-Bench 2.059.3Estimate0.50
Claude 4.5 OpusQwenWebBench1197Estimate0.50
Claude 4.5 OpusSkillsBench45.3Estimate0.50
Claude 4.5 OpusNL2Repo43.2Estimate0.50
Claude 4.5 OpusClaw-Eval Avg76.6Estimate0.50
Claude 4.5 OpusClaw-Eval Pass-359.6Estimate0.50
Claude 4.5 OpusQwenClawBench52.3Estimate0.50
Claude 4.5 OpusMMLU-Pro89.5Estimate0.50
Claude 4.5 OpusMMLU-Redux95.6Estimate0.50
Claude 4.5 OpusSuperGPQA70.6Estimate0.50
Claude 4.5 OpusC-Eval92.2Estimate0.50
Claude 4.5 OpusGPQA Diamond87Estimate0.50
Claude 4.5 OpusLiveCodeBench v684.8Estimate0.50
Claude 4.5 OpusHMMT Feb 2592.9Estimate0.50
Claude 4.5 OpusHMMT Feb 2685.3Estimate0.50
Claude 4.5 OpusIMOAnswerBench84Estimate0.50
Claude 4.5 OpusAIME2695.1Estimate0.50
Qwen3.6-35B-A3BSWE-bench Verified73.4Estimate0.50
Qwen3.6-35B-A3BSWE-bench Multilingual67.2Estimate0.50
Qwen3.6-35B-A3BSWE-bench Terminal-Bench 2.028.7Estimate0.50
Qwen3.6-35B-A3BQwenWebBench1536Estimate0.50
Qwen3.6-35B-A3BSkillsBench48.2Estimate0.50
Qwen3.6-35B-A3BNL2Repo29.4Estimate0.50
Qwen3.6-35B-A3BClaw-Eval Avg68.7Estimate0.50
Qwen3.6-35B-A3BClaw-Eval Pass-350Estimate0.50
Qwen3.6-35B-A3BQwenClawBench52.6Estimate0.50
Qwen3.6-35B-A3BMMLU-Pro85.2Estimate0.50
Qwen3.6-35B-A3BMMLU-Redux93.3Estimate0.50
Qwen3.6-35B-A3BSuperGPQA64.7Estimate0.50
Qwen3.6-35B-A3BC-Eval90Estimate0.50
Qwen3.6-35B-A3BGPQA Diamond86Estimate0.50
Qwen3.6-35B-A3BLiveCodeBench v621.4Estimate0.50
Qwen3.6-35B-A3BHMMT Feb 2590.7Estimate0.50
Qwen3.6-35B-A3BHMMT Feb 2683.6Estimate0.50
Qwen3.6-35B-A3BIMOAnswerBench78.9Estimate0.50
Qwen3.6-35B-A3BAIME2692.7Estimate0.50
Qwen3.6-27BSWE-bench Verified77.2Estimate0.50
Qwen3.6-27BSWE-bench Multilingual53.5Estimate0.50
Qwen3.6-27BSWE-bench Terminal-Bench 2.059.3Estimate0.50
Qwen3.6-27BQwenWebBench1487Estimate0.50
Qwen3.6-27BSkillsBench48.2Estimate0.50
Qwen3.6-27BNL2Repo36.2Estimate0.50
Qwen3.6-27BClaw-Eval Avg72.4Estimate0.50
Qwen3.6-27BClaw-Eval Pass-360.6Estimate0.50
Qwen3.6-27BQwenClawBench53.4Estimate0.50
Qwen3.6-27BMMLU-Pro86.2Estimate0.50
Qwen3.6-27BMMLU-Redux93.5Estimate0.50
Qwen3.6-27BSuperGPQA66Estimate0.50
Qwen3.6-27BC-Eval91.4Estimate0.50
Qwen3.6-27BGPQA Diamond87.8Estimate0.50
Qwen3.6-27BLiveCodeBench v624Estimate0.50
Qwen3.6-27BHMMT Feb 2593.8Estimate0.50
Qwen3.6-27BHMMT Feb 2684.3Estimate0.50
Qwen3.6-27BIMOAnswerBench80.8Estimate0.50
Qwen3.6-27BAIME2694.1Estimate0.50
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 caa492e2fbdb.

See the Max planAPI docs
PathReturnsPlan
GET/api/v1/charts/caa492e2fbdbTitle, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/caa492e2fbdb/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/caa492e2fbdb/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/caa492e2fbdb/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
Estimated from the imageAI Model Benchmark Performance ComparisonQwen · Benchmark bar chart · 25 pointsEstimated from the imageReplica 7.8AI Model Benchmarks ComparisonQwen · Benchmark bar chart · 25 pointsEstimated from the imageModel Comparison Across BenchmarksQwen · Benchmark bar chart · 92 pointsEstimated from the imageQwen3.8-Max: Ranks #2arena · Grouped bar chart · 19 pointsEstimated from the imageModel BenchmarksQwen · Benchmark bar chart · 55 pointsEstimated from the imageModel Benchmark ComparisonQwen · Table chart · 58 points

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/caa492e2fbdb.json and /api/charts/caa492e2fbdb.skill.md.