1. Chart data
  2. artificial-analysis
  3. Cost per Intelligence Index
artificial-analysisBenchmark bar chart · 130 points · DeepSeek V4

Cost per Intelligence Index

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

Estimated from the image 54%DeepSeek V4All DeepSeek modelsAll chart data
Chart by artificial-analysis. 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 130 points are free
GroupSeriesValue (USD)SourceConf.
GPT-5.1 (high)Answer~0.05Estimate0.50
GPT-5.1 (high)Reasoning~0.05Estimate0.50
GPT-5.1 (high)Cache Write~0.05Estimate0.50
GPT-5.1 (high)Cache Hit~0.05Estimate0.50
GPT-5.1 (high)Input~0.05Estimate0.50
DeepSeek V4 (high)Answer0.05Estimate0.97
DeepSeek V4 (high)Reasoning~0.05Estimate0.50
DeepSeek V4 (high)Cache Write~0.05Estimate0.50
DeepSeek V4 (high)Cache Hit~0.05Estimate0.50
DeepSeek V4 (high)Input~0.05Estimate0.50

Max data, free with your email for now

See all 130 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

Nemotron 3.5 (high)Answer0.06Estimate0.97
Nemotron 3.5 (high)Reasoning~0.06Estimate0.30
Nemotron 3.5 (high)Cache Write~0.06Estimate0.30
Nemotron 3.5 (high)Cache Hit~0.06Estimate0.50
Nemotron 3.5 (high)Input~0.06Estimate0.50
GPT-5.2 (high)Answer~0.07Estimate0.50
GPT-5.2 (high)Reasoning~0.07Estimate0.50
GPT-5.2 (high)Cache Write~0.07Estimate0.50
GPT-5.2 (high)Cache Hit~0.07Estimate0.50
GPT-5.2 (high)Input~0.07Estimate0.50
Muse Grimmt (high)Answer0.07Estimate0.97
Muse Grimmt (high)Reasoning~0.07Estimate0.50
Muse Grimmt (high)Cache Write~0.07Estimate0.50
Muse Grimmt (high)Cache Hit~0.07Estimate0.50
Muse Grimmt (high)Input~0.07Estimate0.50
Gemini 3.5 Flash-Lite (high)Answer0.1Estimate0.97
Gemini 3.5 Flash-Lite (high)Reasoning~0.1Estimate0.50
Gemini 3.5 Flash-Lite (high)Cache Write~0.1Estimate0.50
Gemini 3.5 Flash-Lite (high)Cache Hit~0.1Estimate0.50
Gemini 3.5 Flash-Lite (high)Input~0.1Estimate0.50
DeepSeek V3.1 (high)Answer0.11Estimate0.97
DeepSeek V3.1 (high)Reasoning~0.11Estimate0.50
DeepSeek V3.1 (high)Cache Write~0.11Estimate0.50
DeepSeek V3.1 (high)Cache Hit~0.11Estimate0.50
DeepSeek V3.1 (high)Input~0.11Estimate0.50
MiniMax-M3Answer0.14Estimate0.97
MiniMax-M3Reasoning~0.14Estimate0.50
MiniMax-M3Cache Write~0.14Estimate0.50
MiniMax-M3Cache Hit~0.14Estimate0.50
MiniMax-M3Input~0.14Estimate0.50
4.5 Flash (high)Answer~0.22Estimate0.50
4.5 Flash (high)Reasoning~0.22Estimate0.50
4.5 Flash (high)Cache Write~0.22Estimate0.50
4.5 Flash (high)Cache Hit~0.22Estimate0.50
4.5 Flash (high)Input~0.22Estimate0.50
Nemotron Super (high)Answer~0.23Estimate0.50
Nemotron Super (high)Reasoning~0.23Estimate0.50
Nemotron Super (high)Cache Write~0.23Estimate0.50
Nemotron Super (high)Cache Hit~0.23Estimate0.50
Nemotron Super (high)Input~0.23Estimate0.50
Pro 0B3 (high)Answer~0.25Estimate0.50
Pro 0B3 (high)Reasoning~0.25Estimate0.50
Pro 0B3 (high)Cache Write~0.25Estimate0.50
Pro 0B3 (high)Cache Hit~0.25Estimate0.50
Pro 0B3 (high)Input~0.25Estimate0.50
GLM-5.2 (high)Answer0.32Estimate0.97
GLM-5.2 (high)Reasoning~0.32Estimate0.50
GLM-5.2 (high)Cache Write~0.32Estimate0.50
GLM-5.2 (high)Cache Hit~0.32Estimate0.50
GLM-5.2 (high)Input~0.32Estimate0.50
InfernoAnswer0.34Estimate0.97
InfernoReasoning~0.34Estimate0.50
InfernoCache Write~0.34Estimate0.50
InfernoCache Hit~0.34Estimate0.50
InfernoInput~0.34Estimate0.50
Nemotron 5 Ultra (high)Answer~0.38Estimate0.50
Nemotron 5 Ultra (high)Reasoning~0.38Estimate0.50
Nemotron 5 Ultra (high)Cache Write~0.38Estimate0.50
Nemotron 5 Ultra (high)Cache Hit~0.38Estimate0.50
Nemotron 5 Ultra (high)Input~0.38Estimate0.50
Muse 12 (high)Answer0.4Estimate0.97
Muse 12 (high)Reasoning~0.4Estimate0.50
Muse 12 (high)Cache Write~0.4Estimate0.50
Muse 12 (high)Cache Hit~0.4Estimate0.50
Muse 12 (high)Input~0.4Estimate0.50
Gemini 3.7 Flash (high)Answer0.4Estimate0.97
Gemini 3.7 Flash (high)Reasoning~0.4Estimate0.50
Gemini 3.7 Flash (high)Cache Write~0.4Estimate0.50
Gemini 3.7 Flash (high)Cache Hit~0.4Estimate0.50
Gemini 3.7 Flash (high)Input~0.4Estimate0.50
Medium (high)Answer~0.51Estimate0.50
Medium (high)Reasoning~0.51Estimate0.50
Medium (high)Cache Write~0.51Estimate0.50
Medium (high)Cache Hit~0.51Estimate0.50
Medium (high)Input~0.51Estimate0.50
Terra (high)Answer~0.51Estimate0.50
Terra (high)Reasoning~0.51Estimate0.50
Terra (high)Cache Write~0.51Estimate0.50
Terra (high)Cache Hit~0.51Estimate0.50
Terra (high)Input~0.51Estimate0.50
Grok 4.5 (high)Answer0.84Estimate0.97
Grok 4.5 (high)Reasoning~0.84Estimate0.50
Grok 4.5 (high)Cache Write~0.84Estimate0.50
Grok 4.5 (high)Cache Hit~0.84Estimate0.50
Grok 4.5 (high)Input~0.84Estimate0.50
Kimi K3 (high)Answer0.84Estimate0.97
Kimi K3 (high)Reasoning~0.84Estimate0.50
Kimi K3 (high)Cache Write~0.84Estimate0.50
Kimi K3 (high)Cache Hit~0.84Estimate0.50
Kimi K3 (high)Input~0.84Estimate0.50
Owen3.8 MaxAnswer~1.13Estimate0.50
Owen3.8 MaxReasoning~1.13Estimate0.50
Owen3.8 MaxCache Write~1.13Estimate0.50
Owen3.8 MaxCache Hit~1.13Estimate0.50
Owen3.8 MaxInput~1.13Estimate0.50
GPT-5.1 (max)Answer~1.23Estimate0.50
GPT-5.1 (max)Reasoning~1.23Estimate0.50
GPT-5.1 (max)Cache Write~1.23Estimate0.50
GPT-5.1 (max)Cache Hit~1.23Estimate0.50
GPT-5.1 (max)Input~1.23Estimate0.50
Claude Opus 5 (max)Answer~2.34Estimate0.50
Claude Opus 5 (max)Reasoning~2.34Estimate0.50
Claude Opus 5 (max)Cache Write~2.34Estimate0.50
Claude Opus 5 (max)Cache Hit~2.34Estimate0.50
Claude Opus 5 (max)Input~2.34Estimate0.50
Claude Opus 5 (with failback)Answer~3.14Estimate0.50
Claude Opus 5 (with failback)Reasoning~3.14Estimate0.50
Claude Opus 5 (with failback)Cache Write~3.14Estimate0.50
Claude Opus 5 (with failback)Cache Hit~3.14Estimate0.50
Claude Opus 5 (with failback)Input~3.14Estimate0.50
GPT-5.6 (mini)~0.05Estimate0.50
GPT-5.5 (128b)~0.07Estimate0.50
Claude 4.5 (Haiku)~0.22Estimate0.50
DeepSeek V3.2 (mini)~0.25Estimate0.50
Mistral Medium 3~0.46Estimate0.50
Tera (mini)~0.51Estimate0.50
Qwen3.8 (Max)~1.13Estimate0.50
GPT-5.6 (max)~1.23Estimate0.50
Claude 4.5 (Sonnet)~2.34Estimate0.50
Claude 4.5 (Opus)~3.14Estimate0.50
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 c2440b8650cd.

See the Max planAPI docs
PathReturnsPlan
GET/api/v1/charts/c2440b8650cdTitle, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/c2440b8650cd/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/c2440b8650cd/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/c2440b8650cd/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 DeepSeek

All chart data
Partly publisher's numbersReplica 8.1Accuracy / Percentile (%)DeepSeek · Benchmark bar chart · 30 pointsEstimated from the imageGlobal KV Cache Per Token (Bytes)DeepSeek · Bar chart · 4 pointsEstimated from the imageReplica 6.3AI Model Benchmark Performance Comparisonqwen · Benchmark bar chart · 25 pointsPartly publisher's numbersReplica 8.3Accuracy / Percentile (%)DeepSeek · Benchmark bar chart · 30 pointsPartly publisher's numbersAccuracy / Percentile (%)DeepSeek · Benchmark bar chart · 36 pointsEstimated from the imageReplica 9.0AI Model Benchmarks ComparisonDeepSeek · Benchmark bar chart · 20 points

Questions people ask

How accurate are these numbers?

They are estimated from the image by two independent passes, with confidence 0.54 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 artificial-analysis 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/c2440b8650cd.json and /api/charts/c2440b8650cd.skill.md.