1. Chart data
  2. arena
  3. What kinds of failures are flagged?
arenaTable chart · 115 points · Claude Opus 5

What kinds of failures are flagged?

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

Estimated from the image 50%Claude Opus 5All Anthropic modelsAll chart data
Chart by arena. 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 115 points are free
GroupSeriesValueSourceConf.
Claude Fable 5.1Cleanup~6.5%Estimate0.50
Claude Opus 4.8Cleanup~30.4%Estimate0.50
Claude Opus 5Cleanup~53.5%Estimate0.50
Claude Sonnet 5Cleanup~38%Estimate0.50
Claude Opus 5.5Cleanup~32%Estimate0.50
Claude Sonnet 5.5 HighCleanup~32.8%Estimate0.50
DeepGLM V4.1 FlashCleanup~26%Estimate0.50
GPT-5.6 SolCleanup~45.2%Estimate0.50
GPT-6 AstraCleanup~16%Estimate0.50
GPT-6 LunaCleanup~35.3%Estimate0.50

Max data, free with your email for now

See all 115 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

GPT-6 SolCleanup~21.4%Estimate0.50
GPT-6.1 SolCleanup~13.3%Estimate0.50
Gemini 3.6 FlashCleanup~13.6%Estimate0.50
Gemini 3.7 FlashCleanup~25%Estimate0.50
Gemini 4 ArgonCleanup~45.3%Estimate0.50
Grok 4.6Cleanup~30%Estimate0.50
Grok 4.7Cleanup~37.5%Estimate0.50
HY4 PreviewCleanup~22%Estimate0.50
Kimi K3Cleanup~33.8%Estimate0.50
MiniMax M3Cleanup~26.9%Estimate0.50
Muse Spark 1.3BCleanup~22.7%Estimate0.50
Qwen3.8 27BCleanup~24.6%Estimate0.50
Qwen3.8 MaxCleanup~31.2%Estimate0.50
Claude Fable 5.1Extra outputs~16.1%Estimate0.50
Claude Opus 4.8Extra outputs~26.1%Estimate0.50
Claude Opus 5Extra outputs~32.4%Estimate0.50
Claude Sonnet 5Extra outputs~40%Estimate0.50
Claude Opus 5.5Extra outputs~14%Estimate0.50
Claude Sonnet 5.5 HighExtra outputs~39.1%Estimate0.50
DeepGLM V4.1 FlashExtra outputs~27.4%Estimate0.50
GPT-5.6 SolExtra outputs~14.3%Estimate0.50
GPT-6 AstraExtra outputs~23.5%Estimate0.50
GPT-6 LunaExtra outputs~25%Estimate0.50
GPT-6 SolExtra outputs~25%Estimate0.50
GPT-6.1 SolExtra outputs~33.3%Estimate0.50
Gemini 3.6 FlashExtra outputs~21.6%Estimate0.50
Gemini 3.7 FlashExtra outputs~20.8%Estimate0.50
Gemini 4 ArgonExtra outputs~20.3%Estimate0.50
Grok 4.6Extra outputs~23.3%Estimate0.50
Grok 4.7Extra outputs~40%Estimate0.50
HY4 PreviewExtra outputs~30%Estimate0.50
Kimi K3Extra outputs~22.1%Estimate0.50
MiniMax M3Extra outputs~7.5%Estimate0.50
Muse Spark 1.3BExtra outputs~13.6%Estimate0.50
Qwen3.8 27BExtra outputs~24.6%Estimate0.50
Qwen3.8 MaxExtra outputs~21.2%Estimate0.50
Claude Fable 5.1Premature execution~38.7%Estimate0.50
Claude Opus 4.8Premature execution~18.8%Estimate0.50
Claude Opus 5Premature execution~28.2%Estimate0.50
Claude Sonnet 5Premature execution~26%Estimate0.50
Claude Opus 5.5Premature execution~18%Estimate0.50
Claude Sonnet 5.5 HighPremature execution~18%Estimate0.50
DeepGLM V4.1 FlashPremature execution~19.2%Estimate0.50
GPT-5.6 SolPremature execution~23.8%Estimate0.50
GPT-6 AstraPremature execution~20%Estimate0.50
GPT-6 LunaPremature execution~23.5%Estimate0.50
GPT-6 SolPremature execution~21.4%Estimate0.50
GPT-6.1 SolPremature execution~14.3%Estimate0.50
Gemini 3.6 FlashPremature execution~31.3%Estimate0.50
Gemini 3.7 FlashPremature execution~29.6%Estimate0.50
Gemini 4 ArgonPremature execution~33.3%Estimate0.50
Grok 4.6Premature execution~14.4%Estimate0.50
Grok 4.7Premature execution~30%Estimate0.50
HY4 PreviewPremature execution~22.5%Estimate0.50
Kimi K3Premature execution~13.2%Estimate0.50
MiniMax M3Premature execution~30%Estimate0.50
Muse Spark 1.3BPremature execution~38.6%Estimate0.50
Qwen3.8 27BPremature execution~30.8%Estimate0.50
Qwen3.8 MaxPremature execution~22.5%Estimate0.50
Claude Fable 5.1Scope expansion~16.1%Estimate0.50
Claude Opus 4.8Scope expansion~15.9%Estimate0.50
Claude Opus 5Scope expansion~22.5%Estimate0.50
Claude Sonnet 5Scope expansion~0%Estimate0.50
Claude Opus 5.5Scope expansion~26%Estimate0.50
Claude Sonnet 5.5 HighScope expansion~26%Estimate0.50
DeepGLM V4.1 FlashScope expansion~18.8%Estimate0.50
GPT-5.6 SolScope expansion~19%Estimate0.50
GPT-6 AstraScope expansion~24%Estimate0.50
GPT-6 LunaScope expansion~11.8%Estimate0.50
GPT-6 SolScope expansion~10.7%Estimate0.50
GPT-6.1 SolScope expansion~28.6%Estimate0.50
Gemini 3.6 FlashScope expansion~24.2%Estimate0.50
Gemini 3.7 FlashScope expansion~29.6%Estimate0.50
Gemini 4 ArgonScope expansion~25%Estimate0.50
Grok 4.6Scope expansion~14.1%Estimate0.50
Grok 4.7Scope expansion~10%Estimate0.50
HY4 PreviewScope expansion~20%Estimate0.50
Kimi K3Scope expansion~22.1%Estimate0.50
MiniMax M3Scope expansion~22.5%Estimate0.50
Muse Spark 1.3BScope expansion~22.7%Estimate0.50
Qwen3.8 27BScope expansion~22.5%Estimate0.50
Qwen3.8 MaxScope expansion~22.5%Estimate0.50
Claude Fable 5.1Protected content~12.9%Estimate0.50
Claude Opus 4.8Protected content~14.5%Estimate0.50
Claude Opus 5Protected content~4.2%Estimate0.50
Claude Sonnet 5Protected content~12%Estimate0.50
Claude Opus 5.5Protected content~20%Estimate0.50
Claude Sonnet 5.5 HighProtected content~8%Estimate0.50
DeepGLM V4.1 FlashProtected content~7.8%Estimate0.50
GPT-5.6 SolProtected content~9.5%Estimate0.50
GPT-6 AstraProtected content~8%Estimate0.50
GPT-6 LunaProtected content~5.9%Estimate0.50
GPT-6 SolProtected content~7.1%Estimate0.50
GPT-6.1 SolProtected content~7.1%Estimate0.50
Gemini 3.6 FlashProtected content~20.2%Estimate0.50
Gemini 3.7 FlashProtected content~20%Estimate0.50
Gemini 4 ArgonProtected content~18.5%Estimate0.50
Grok 4.6Protected content~7.8%Estimate0.50
Grok 4.7Protected content~6.7%Estimate0.50
HY4 PreviewProtected content~23%Estimate0.50
Kimi K3Protected content~5.9%Estimate0.50
MiniMax M3Protected content~10%Estimate0.50
Muse Spark 1.3BProtected content~2.3%Estimate0.50
Qwen3.8 27BProtected content~7.7%Estimate0.50
Qwen3.8 MaxProtected content~10%Estimate0.50
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 585a868f210c.

See the Max planAPI docs
PathReturnsPlan
GET/api/v1/charts/585a868f210cTitle, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/585a868f210c/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/585a868f210c/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/585a868f210c/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 Anthropic

All chart data
Estimated from the imageClaude 3.5 Sonnet benchmarksAnthropic · Table chart · 34 pointsEstimated from the imageSoftware engineeringAnthropic · Bar chart · 2 pointsEstimated from the imageNovel problem-solving by costAnthropic · Scatter plot · 3 pointsEstimated from the imageReplica 7.4Code Arena: WebDevarena · Bar chart · 15 pointsEstimated from the imageModel benchmarksAnthropic · Table chart · 31 pointsEstimated from the imageReplica 6.0Opus 4.8Anthropic · Table chart · 28 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 arena 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/585a868f210c.json and /api/charts/585a868f210c.skill.md.