1. Chart data
  2. artificial-analysis
  3. Cost per Intelligence Index
artificial-analysisBenchmark bar chart · 114 points · Kimi K3

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 41%Kimi K3All Kimi (Moonshot AI) 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 114 points are free
GroupSeriesValue (USD)SourceConf.
DeepSeek-R1 (Distill)Answer~0.03Estimate0.50
DeepSeek-R1 (Distill)Reasoning~0Estimate0.30
DeepSeek-R1 (Distill)Cache Write~0Estimate0.30
DeepSeek-R1 (Distill)Cache Hit~0Estimate0.30
DeepSeek-R1 (Distill)Input~0Estimate0.30
MiniMax-M1Answer0.03Estimate0.97
MiniMax-M1Reasoning~0Estimate0.30
MiniMax-M1Cache Write~0Estimate0.30
MiniMax-M1Cache Hit~0Estimate0.30
MiniMax-M1Input~0Estimate0.30

Max data, free with your email for now

See all 114 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-5.1 (High)Answer~0.05Estimate0.50
GPT-5.1 (High)Reasoning~0Estimate0.30
GPT-5.1 (High)Cache Write~0Estimate0.30
GPT-5.1 (High)Cache Hit~0Estimate0.30
GPT-5.1 (High)Input~0Estimate0.30
Gemini 3.1 Flash-ThinkingAnswer~0.1Estimate0.50
Gemini 3.1 Flash-ThinkingReasoning~0Estimate0.30
Gemini 3.1 Flash-ThinkingCache Write~0Estimate0.30
Gemini 3.1 Flash-ThinkingCache Hit~0Estimate0.30
Gemini 3.1 Flash-ThinkingInput~0Estimate0.30
Mistral-M3Answer~0.14Estimate0.50
Mistral-M3Reasoning~0Estimate0.30
Mistral-M3Cache Write~0Estimate0.30
Mistral-M3Cache Hit~0Estimate0.30
Mistral-M3Input~0Estimate0.30
Claude 4.5 HaikuAnswer0.22Estimate0.97
Claude 4.5 HaikuReasoning~0Estimate0.30
Claude 4.5 HaikuCache Write~0Estimate0.30
Claude 4.5 HaikuCache Hit~0Estimate0.30
Claude 4.5 HaikuInput~0Estimate0.30
Grok 4.5 (High)Answer0.36Estimate0.97
Grok 4.5 (High)Reasoning~0Estimate0.30
Grok 4.5 (High)Cache Write~0Estimate0.30
Grok 4.5 (High)Cache Hit~0Estimate0.30
Grok 4.5 (High)Input~0Estimate0.30
NanoBanana 3 UltraAnswer0.38Estimate0.97
NanoBanana 3 UltraReasoning~0.31Estimate0.50
NanoBanana 3 UltraCache Write~0Estimate0.30
NanoBanana 3 UltraCache Hit~0Estimate0.30
NanoBanana 3 UltraInput~0Estimate0.30
Mistral Medium 3.1Answer~0.4Estimate0.50
Mistral Medium 3.1Reasoning~0.16Estimate0.50
Mistral Medium 3.1Cache Write~0Estimate0.30
Mistral Medium 3.1Cache Hit~0Estimate0.30
Mistral Medium 3.1Input~0Estimate0.30
Gemini 3.1 Pro (High)Answer~0.46Estimate0.50
Gemini 3.1 Pro (High)Reasoning~0.16Estimate0.50
Gemini 3.1 Pro (High)Cache Write~0Estimate0.30
Gemini 3.1 Pro (High)Cache Hit~0Estimate0.30
Gemini 3.1 Pro (High)Input~0Estimate0.30
OpenAI o3 (High)Answer~0.51Estimate0.50
OpenAI o3 (High)Reasoning~0.18Estimate0.50
OpenAI o3 (High)Cache Write~0Estimate0.30
OpenAI o3 (High)Cache Hit~0Estimate0.30
OpenAI o3 (High)Input~0Estimate0.30
Qwen3.7 MaxAnswer~0.53Estimate0.50
Qwen3.7 MaxReasoning~0.18Estimate0.50
Qwen3.7 MaxCache Write~0Estimate0.30
Qwen3.7 MaxCache Hit~0Estimate0.30
Qwen3.7 MaxInput~0Estimate0.30
Gemini 3.1 FlashAnswer~0.56Estimate0.50
Gemini 3.1 FlashReasoning~0.22Estimate0.50
Gemini 3.1 FlashCache Write~0Estimate0.30
Gemini 3.1 FlashCache Hit~0Estimate0.30
Gemini 3.1 FlashInput~0Estimate0.30
GLM-5.2 (High)Answer0.57Estimate0.97
GLM-5.2 (High)Reasoning~0.27Estimate0.50
GLM-5.2 (High)Cache Write~0Estimate0.30
GLM-5.2 (High)Cache Hit~0Estimate0.30
GLM-5.2 (High)Input~0Estimate0.30
Kim K2 (High)Answer0.86Estimate0.97
Kim K2 (High)Reasoning~0.19Estimate0.50
Kim K2 (High)Cache Write~0Estimate0.30
Kim K2 (High)Cache Hit~0Estimate0.30
Kim K2 (High)Input~0Estimate0.30
OpenAI o3.9 MaxAnswer~1.14Estimate0.50
OpenAI o3.9 MaxReasoning~0.28Estimate0.50
OpenAI o3.9 MaxCache Write~0.55Estimate0.50
OpenAI o3.9 MaxCache Hit~0Estimate0.30
OpenAI o3.9 MaxInput~0Estimate0.30
GPT-5.2 (High)Answer1.23Estimate0.97
GPT-5.2 (High)Reasoning~0.48Estimate0.30
GPT-5.2 (High)Cache Write~0.69Estimate0.30
GPT-5.2 (High)Cache Hit~0Estimate0.30
GPT-5.2 (High)Input~0Estimate0.30
Claude Opus 4.5 (High)Answer~1.72Estimate0.30
Claude Opus 4.5 (High)Reasoning~0.58Estimate0.30
Claude Opus 4.5 (High)Cache Write~0.88Estimate0.30
Claude Opus 4.5 (High)Cache Hit~0Estimate0.30
Claude Opus 4.5 (High)Input~0Estimate0.30
Claude Opus 4.5 (High)Answer~2.03Estimate0.50
Claude Opus 4.5 (High)Reasoning~0.5Estimate0.50
Claude Opus 4.5 (High)Cache Write~0.37Estimate0.50
Claude Opus 4.5 (High)Cache Hit~0Estimate0.30
Claude Opus 4.5 (High)Input~0Estimate0.30
Claude Opus 4.5 (High)Answer~2.34Estimate0.50
Claude Opus 4.5 (High)Reasoning~0.64Estimate0.50
Claude Opus 4.5 (High)Cache Write~0.87Estimate0.50
Claude Opus 4.5 (High)Cache Hit~0Estimate0.30
Claude Opus 4.5 (High)Input~0Estimate0.30
Claude Opus 4.5 (High)Answer~3.15Estimate0.50
Claude Opus 4.5 (High)Reasoning~0.43Estimate0.50
Claude Opus 4.5 (High)Cache Write~1.26Estimate0.50
Claude Opus 4.5 (High)Cache Hit~0.59Estimate0.50
Claude Opus 4.5 (High)Input~0.78Estimate0.50
DeepSeek-V3 (DeepSeek)~0.03Estimate0.50
Gemini 3.5 Flash (Google)~0.1Estimate0.50
MiniMax-M2 (MiniMax)~0.14Estimate0.50
Mistral Medium 3 (Mistral)~0.4Estimate0.50
Gemini 3.5 Pro (Google)~0.46Estimate0.50
Owen3.7 Max (Alibaba)~0.51Estimate0.50
Gemini 3.5 Flash (Google)~0.56Estimate0.50
Owen3.8 Max (Alibaba)~1.14Estimate0.50
Claude Sonnet 4.5 (Anthropic)~1.72Estimate0.50
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 9acd3210e400.

Approximate values. Our two readings of this chart agreed only in part (confidence 0.41 of 1), so check the original before you quote a number. The API marks it lowConfidence, and ?min_confidence=0.5 leaves it out.

See the Max planAPI docs
PathReturnsPlan
GET/api/v1/charts/9acd3210e400Title, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/9acd3210e400/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/9acd3210e400/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/9acd3210e400/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 Kimi (Moonshot AI)

All chart data
Estimated from the imageReplica 9.0Model Performance ComparisonKimi (Moonshot AI) · Benchmark bar chart · 15 pointsEstimated from the imageModel BenchmarksKimi (Moonshot AI) · Benchmark bar chart · 47 pointsEstimated from the imageReplica 7.9Coding and Agents BenchmarksKimi (Moonshot AI) · Benchmark bar chart · 24 pointsEstimated from the imageModel Performance ComparisonKimi (Moonshot AI) · Benchmark bar chart · 38 pointsEstimated from the imageInternal Knowledge Work BenchKimi (Moonshot AI) · Benchmark bar chart · 9 pointsEstimated from the imageReplica 6.3Frontend Code Kimi-K3: Ranked #1arena · Bar chart · 23 points

Questions people ask

How accurate are these numbers?

They are estimated from the image by two independent passes, with confidence 0.41 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/9acd3210e400.json and /api/charts/9acd3210e400.skill.md.