1. Chart data
  2. Kimi (Moonshot AI)
  3. Model Benchmarks
Kimi (Moonshot AI)Benchmark bar chart · 47 points · Kimi K2

Model Benchmarks

The numbers behind a chart Kimi (Moonshot AI) published, redrawn natively. Check the original, study the data, then make your own.

Estimated from the image 93%Kimi K2All Kimi (Moonshot AI) modelsAll chart data
Chart by Kimi (Moonshot AI). Source: huggingface.co

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 47 points are free
GroupSeriesValueSourceConf.
Kimi-K2-InstructSWE-bench Verified65.8Estimate0.97
DeepSeek-V3.0324SWE-bench Verified37.7Estimate0.90
Qwen3-235B-A22BSWE-bench Verified34.4Estimate0.97
Claude 4 OpusSWE-bench Verified72.5Estimate0.97
Kimi-K2-InstructSWE-bench Multilingual47.3Estimate0.97
DeepSeek-V3.0324SWE-bench Multilingual25.6Estimate0.97
Qwen3-235B-A22BSWE-bench Multilingual20.9Estimate0.97
Claude 4 SonnetSWE-bench Multilingual31Estimate0.50
Kimi-K2-InstructLiveCodeBench v653.7Estimate0.97
DeepSeek-V3.0324LiveCodeBench v646.9Estimate0.97

Max data, free with your email for now

See all 47 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

Qwen3-235B-A22BLiveCodeBench v637Estimate0.97
OpenAI GPT-4.1LiveCodeBench v644.7Estimate0.97
Claude 4 OpusLiveCodeBench v647.4Estimate0.97
Gemini 2.5 FlashLiveCodeBench v644.7Estimate0.97
Kimi-K2-InstructOJBench27.1Estimate0.97
DeepSeek-V3.0324OJBench24Estimate0.97
Qwen3-235B-A22BOJBench11.3Estimate0.97
OpenAI GPT-4.1OJBench19.5Estimate0.97
Claude 4 OpusOJBench19.6Estimate0.97
Gemini 2.5 FlashOJBench19.5Estimate0.97
Kimi-K2-InstructTau2-bench weighted66.1Estimate0.97
DeepSeek-V3.0324Tau2-bench weighted48.7Estimate0.97
Qwen3-235B-A22BTau2-bench weighted37.3Estimate0.97
OpenAI GPT-4.1Tau2-bench weighted54.4Estimate0.97
Claude 4 OpusTau2-bench weighted67.6Estimate0.97
Gemini 2.5 FlashTau2-bench weighted41Estimate0.97
Kimi-K2-InstructAceBench(en)76.5Estimate0.97
DeepSeek-V3.0324AceBench(en)72.7Estimate0.97
Qwen3-235B-A22BAceBench(en)70.5Estimate0.97
OpenAI GPT-4.1AceBench(en)80.1Estimate0.97
Claude 4 OpusAceBench(en)75.6Estimate0.97
Gemini 2.5 FlashAceBench(en)74.5Estimate0.97
Kimi-K2-InstructAIME 202549.5Estimate0.97
DeepSeek-V3.0324AIME 202547.55Estimate0.90
Qwen3-235B-A22BAIME 202524.7Estimate0.97
OpenAI GPT-4.1AIME 202537Estimate0.97
Claude 4 OpusAIME 202533.9Estimate0.97
Gemini 2.5 FlashAIME 202546.6Estimate0.97
Kimi-K2-InstructGPQA-Diamond75.1Estimate0.97
DeepSeek-V3.0324GPQA-Diamond68.4Estimate0.97
Qwen3-235B-A22BGPQA-Diamond62.9Estimate0.97
OpenAI GPT-4.1GPQA-Diamond66.3Estimate0.97
Claude 4 OpusGPQA-Diamond74.9Estimate0.97
Gemini 2.5 FlashGPQA-Diamond68.2Estimate0.97
OpenAI GPT-4.1SWE-bench Verified54.6Estimate0.50
OpenAI GPT-4.1SWE-bench Multilingual31.5Estimate0.50
Claude 4 OpusSWE-bench Multilingual51Estimate0.50
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 04d714dfca48.

See the Max planAPI docs
PathReturnsPlan
GET/api/v1/charts/04d714dfca48Title, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/04d714dfca48/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/04d714dfca48/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/04d714dfca48/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 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 pointsEstimated from the imageOmniDocBench Scores by CategoryKimi (Moonshot AI) · Benchmark bar chart · 44 points

Questions people ask

How accurate are these numbers?

They are estimated from the image by two independent passes, with confidence 0.93 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 Kimi (Moonshot AI) 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/04d714dfca48.json and /api/charts/04d714dfca48.skill.md.