1. Chart data
  2. Qwen
  3. Qwen3-Coder Benchmarks
QwenTable chart · 135 points · Qwen Coder

Qwen3-Coder Benchmarks

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 135 points are free
GroupSeriesValueSourceConf.
Terminal-BenchQwen3-Coder 480B-A3B-Instruct37.5Estimate0.50
Terminal-BenchQwen3-Coder 480B-A3B-Instruct69.6Estimate0.50
Terminal-BenchQwen3-Coder 480B-A3B-Instruct67Estimate0.50
Terminal-BenchQwen3-Coder 480B-A3B-Instruct54.7Estimate0.50
Terminal-BenchQwen3-Coder 480B-A3B-Instruct25.8Estimate0.50
Terminal-BenchQwen3-Coder 480B-A3B-Instruct27Estimate0.50
Terminal-BenchQwen3-Coder 480B-A3B-Instruct61.8Estimate0.50
Terminal-BenchQwen3-Coder 480B-A3B-Instruct31.1Estimate0.50
Terminal-BenchQwen3-Coder 480B-A3B-Instruct31.1Estimate0.50
Terminal-BenchKimi-K2 Instruct30Estimate0.50

Max data, free with your email for now

See all 135 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

Terminal-BenchKimi-K2 Instruct65.8Estimate0.50
Terminal-BenchKimi-K2 Instruct65.4Estimate0.50
Terminal-BenchKimi-K2 Instruct47.3Estimate0.50
Terminal-BenchKimi-K2 Instruct19.8Estimate0.50
Terminal-BenchKimi-K2 Instruct20.7Estimate0.50
Terminal-BenchKimi-K2 Instruct60Estimate0.50
Terminal-BenchKimi-K2 Instruct25.2Estimate0.50
Terminal-BenchKimi-K2 Instruct25.2Estimate0.50
Terminal-BenchDeepSeek-V3 03242.5Estimate0.50
Terminal-BenchDeepSeek-V3 032438.8Estimate0.50
Terminal-BenchDeepSeek-V3 032413Estimate0.50
Terminal-BenchDeepSeek-V3 032413Estimate0.50
Terminal-BenchDeepSeek-V3 03247.5Estimate0.50
Terminal-BenchDeepSeek-V3 03247.5Estimate0.50
Terminal-BenchDeepSeek-V3 032456.9Estimate0.50
Terminal-BenchDeepSeek-V3 032412.8Estimate0.50
Terminal-BenchDeepSeek-V3 032412.8Estimate0.50
Terminal-BenchClaude Sonnet-435.5Estimate0.50
Terminal-BenchClaude Sonnet-472.7Estimate0.50
Terminal-BenchClaude Sonnet-468Estimate0.50
Terminal-BenchClaude Sonnet-453.3Estimate0.50
Terminal-BenchClaude Sonnet-424.8Estimate0.50
Terminal-BenchClaude Sonnet-425Estimate0.50
Terminal-BenchClaude Sonnet-456.4Estimate0.50
Terminal-BenchClaude Sonnet-431.1Estimate0.50
Terminal-BenchClaude Sonnet-431.1Estimate0.50
Terminal-BenchOpenAI GPT-4.125.3Estimate0.50
Terminal-BenchOpenAI GPT-4.148.6Estimate0.50
Terminal-BenchOpenAI GPT-4.131.5Estimate0.50
Terminal-BenchOpenAI GPT-4.131.5Estimate0.50
Terminal-BenchOpenAI GPT-4.116.5Estimate0.50
Terminal-BenchOpenAI GPT-4.116.5Estimate0.50
Terminal-BenchOpenAI GPT-4.152.4Estimate0.50
Terminal-BenchOpenAI GPT-4.116.5Estimate0.50
Terminal-BenchOpenAI GPT-4.116.5Estimate0.50
Agentic Browser UseQwen3-Coder 480B-A3B-Instruct49.9Estimate0.50
Agentic Browser UseQwen3-Coder 480B-A3B-Instruct55.8Estimate0.50
Agentic Browser UseKimi-K2 Instruct47.4Estimate0.50
Agentic Browser UseKimi-K2 Instruct42.7Estimate0.50
Agentic Browser UseDeepSeek-V3 032440Estimate0.50
Agentic Browser UseDeepSeek-V3 032436Estimate0.50
Agentic Browser UseClaude Sonnet-451.1Estimate0.50
Agentic Browser UseClaude Sonnet-447.4Estimate0.50
Agentic Browser UseOpenAI GPT-4.144.3Estimate0.50
Agentic Browser UseOpenAI GPT-4.149.6Estimate0.50
Agentic Tool UseQwen3-Coder 480B-A3B-Instruct68.7Estimate0.50
Agentic Tool UseQwen3-Coder 480B-A3B-Instruct77.5Estimate0.50
Agentic Tool UseQwen3-Coder 480B-A3B-Instruct60Estimate0.50
Agentic Tool UseKimi-K2 Instruct65.2Estimate0.50
Agentic Tool UseKimi-K2 Instruct70.7Estimate0.50
Agentic Tool UseKimi-K2 Instruct53.5Estimate0.50
Agentic Tool UseDeepSeek-V3 032456.9Estimate0.50
Agentic Tool UseDeepSeek-V3 032459.1Estimate0.50
Agentic Tool UseDeepSeek-V3 032440Estimate0.50
Agentic Tool UseClaude Sonnet-473.3Estimate0.50
Agentic Tool UseClaude Sonnet-480.5Estimate0.50
Agentic Tool UseClaude Sonnet-460Estimate0.50
Agentic Tool UseOpenAI GPT-4.162.9Estimate0.50
Agentic Tool UseOpenAI GPT-4.10Estimate0.50
Agentic Tool UseOpenAI GPT-4.10Estimate0.50
SWE-bench VerifiedTerminal-Bench37.5Estimate0.50
SWE-bench Verified w/ OpenHands, 500 turnsTerminal-Bench69.6Estimate0.50
SWE-bench Live w/ OpenHands, 100 turnsTerminal-Bench67Estimate0.50
SWE-bench MultilingualTerminal-Bench54.7Estimate0.50
Multi-SWE-bench miniTerminal-Bench25.8Estimate0.50
Multi-SWE-bench flashTerminal-Bench27Estimate0.50
Aider-PolyglotTerminal-Bench61.8Estimate0.50
Spider2Terminal-Bench31.1Estimate0.50
SWE-bench VerifiedQwen3-Coder 480B-A35B-Instruct30Estimate0.50
SWE-bench Verified w/ OpenHands, 500 turnsQwen3-Coder 480B-A35B-Instruct65.8Estimate0.50
SWE-bench Live w/ OpenHands, 100 turnsQwen3-Coder 480B-A35B-Instruct65.4Estimate0.50
SWE-bench MultilingualQwen3-Coder 480B-A35B-Instruct47.3Estimate0.50
Multi-SWE-bench miniQwen3-Coder 480B-A35B-Instruct19.8Estimate0.50
Multi-SWE-bench flashQwen3-Coder 480B-A35B-Instruct20.7Estimate0.50
Aider-PolyglotQwen3-Coder 480B-A35B-Instruct60Estimate0.50
Spider2Qwen3-Coder 480B-A35B-Instruct25.2Estimate0.50
SWE-bench VerifiedDeepSeek-V32.5Estimate0.50
SWE-bench Verified w/ OpenHands, 500 turnsDeepSeek-V338.8Estimate0.50
SWE-bench Live w/ OpenHands, 100 turnsDeepSeek-V313Estimate0.50
SWE-bench MultilingualDeepSeek-V37.5Estimate0.50
Multi-SWE-bench miniDeepSeek-V37.5Estimate0.50
Multi-SWE-bench flashDeepSeek-V312.8Estimate0.50
Aider-PolyglotDeepSeek-V356.9Estimate0.50
Spider2DeepSeek-V312.8Estimate0.50
SWE-bench VerifiedClaude Sonnet-435.5Estimate0.50
SWE-bench Verified w/ OpenHands, 500 turnsClaude Sonnet-472.7Estimate0.50
SWE-bench Live w/ OpenHands, 100 turnsClaude Sonnet-468Estimate0.50
SWE-bench MultilingualClaude Sonnet-453.3Estimate0.50
Multi-SWE-bench miniClaude Sonnet-424.8Estimate0.50
Multi-SWE-bench flashClaude Sonnet-425Estimate0.50
Aider-PolyglotClaude Sonnet-456.4Estimate0.50
Spider2Claude Sonnet-431.1Estimate0.50
SWE-bench VerifiedOpenAI GPT-4.125.3Estimate0.50
SWE-bench Verified w/ OpenHands, 500 turnsOpenAI GPT-4.148.6Estimate0.50
SWE-bench Live w/ OpenHands, 100 turnsOpenAI GPT-4.131.5Estimate0.50
SWE-bench MultilingualOpenAI GPT-4.131.5Estimate0.50
Multi-SWE-bench miniOpenAI GPT-4.116.5Estimate0.50
Multi-SWE-bench flashOpenAI GPT-4.116.5Estimate0.50
Aider-PolyglotOpenAI GPT-4.152.4Estimate0.50
Spider2OpenAI GPT-4.116.5Estimate0.50
WebArenaWebArena49.9Estimate0.50
Mind2WebWebArena55.8Estimate0.50
WebArenaQwen3-Coder 480B-A35B-Instruct (WebArena)47.4Estimate0.50
Mind2WebQwen3-Coder 480B-A35B-Instruct (WebArena)42.7Estimate0.50
WebArenaDeepSeek-V3 (WebArena)40Estimate0.50
Mind2WebDeepSeek-V3 (WebArena)36Estimate0.50
WebArenaClaude Sonnet-4 (WebArena)51.1Estimate0.50
Mind2WebClaude Sonnet-4 (WebArena)47.4Estimate0.50
WebArenaOpenAI GPT-4.1 (WebArena)44.3Estimate0.50
Mind2WebOpenAI GPT-4.1 (WebArena)49.6Estimate0.50
BFCL-v3BFCL-v368.7Estimate0.50
TAU-Bench RetailBFCL-v377.5Estimate0.50
TAU-Bench AirlineBFCL-v360Estimate0.50
BFCL-v3Qwen3-Coder 480B-A35B-Instruct (Tool Use)65.2Estimate0.50
TAU-Bench RetailQwen3-Coder 480B-A35B-Instruct (Tool Use)70.7Estimate0.50
TAU-Bench AirlineQwen3-Coder 480B-A35B-Instruct (Tool Use)53.5Estimate0.50
BFCL-v3DeepSeek-V3 (Tool Use)56.9Estimate0.50
TAU-Bench RetailDeepSeek-V3 (Tool Use)59.1Estimate0.50
TAU-Bench AirlineDeepSeek-V3 (Tool Use)40Estimate0.50
BFCL-v3Claude Sonnet-4 (Tool Use)73.3Estimate0.50
TAU-Bench RetailClaude Sonnet-4 (Tool Use)60Estimate0.50
TAU-Bench AirlineClaude Sonnet-4 (Tool Use)60Estimate0.50
BFCL-v3OpenAI GPT-4.1 (Tool Use)62.9Estimate0.50
TAU-Bench RetailOpenAI GPT-4.1 (Tool Use)60Estimate0.50
TAU-Bench AirlineOpenAI GPT-4.1 (Tool Use)60Estimate0.50
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 614229d366d8.

See the Max planAPI docs
PathReturnsPlan
GET/api/v1/charts/614229d366d8Title, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/614229d366d8/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/614229d366d8/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/614229d366d8/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/614229d366d8.json and /api/charts/614229d366d8.skill.md.