1. Chart data
  2. Z.ai
  3. LLM Benchmarks: Terminal Bench 2.1, DeepSWE v1.1, Agents' La
Z.aiBenchmark bar chart · 33 points · GLM-5

LLM Benchmarks: Terminal Bench 2.1, DeepSWE v1.1, Agents' Last Exam, AutomationBench v1.0.6, HLE w/ Tools, GDPVal-AA v2

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

Partly publisher's numbers 98%GLM-5GLM-5.3All Z.ai modelsAll chart data
Chart by Z.ai. 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 33 points are free
GroupSeriesValueSourceConf.
Terminal Bench 2.1GLM-5.3-Flash84.3chart says 84.3, model card says 88.2Estimate0.97
Terminal Bench 2.1GLM-5.281Publisher1.00
Terminal Bench 2.1DeepSeek-V4-Vision-Exp83.9Estimate0.97
Terminal Bench 2.1Claude Opus 4.885Estimate0.97
Terminal Bench 2.1GPT-5.6 Terra87.4Estimate0.97
Terminal Bench 2.1Gemini 3.7 Flash85.8Estimate0.97
DeepSWE v1.1GLM-5.3-Flash63.4chart says 63.4, model card says 66.9Estimate0.97
DeepSWE v1.1GLM-5.246.2Publisher1.00
DeepSWE v1.1DeepSeek-V4-Vision-Exp59.3Estimate0.97
DeepSWE v1.1Claude Opus 4.858Estimate0.97

Max data, free with your email for now

See all 33 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

DeepSWE v1.1GPT-5.6 Terra69.6Estimate0.97
DeepSWE v1.1Gemini 3.7 Flash65.3Estimate0.97
Agents' Last ExamGLM-5.3-Flash26.3chart says 26.3, model card says 28.5Estimate0.97
Agents' Last ExamGLM-5.220.4chart says 20.4, model card says 23.8Estimate0.97
Agents' Last ExamDeepSeek-V4-Vision-Exp27.3Estimate0.97
Agents' Last ExamClaude Opus 4.827Estimate0.97
Agents' Last ExamGPT-5.6 Terra28Estimate0.97
AutomationBenchGLM-5.3-Flash48.2Publisher1.00
AutomationBenchGLM-5.226.2Publisher1.00
AutomationBenchDeepSeek-V4-Vision-Exp38.8Estimate0.97
AutomationBenchClaude Opus 4.841Estimate0.97
AutomationBenchGPT-5.6 Terra37.2Estimate0.97
AutomationBenchGemini 3.7 Flash52.3Estimate0.97
HLE w/ ToolsGLM-5.3-Flash55.3chart says 55.3, model card says 62.5Estimate0.97
HLE w/ ToolsGLM-5.254.7Publisher1.00
HLE w/ ToolsDeepSeek-V4-Vision-Exp55.1Estimate0.97
HLE w/ ToolsClaude Opus 4.857.9Estimate0.97
GDPVal-AA v2GLM-5.3-Flash1769Publisher1.00
GDPVal-AA v2GLM-5.21508Publisher1.00
GDPVal-AA v2DeepSeek-V4-Vision-Exp1675Estimate0.97
GDPVal-AA v2Claude Opus 4.81582Estimate0.97
GDPVal-AA v2GPT-5.6 Terra1571Estimate0.97
GDPVal-AA v2Gemini 3.7 Flash1527Estimate0.97
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 8f5228bd5d9a.

See the Max planAPI docs
PathReturnsPlan
GET/api/v1/charts/8f5228bd5d9aTitle, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/8f5228bd5d9a/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/8f5228bd5d9a/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/8f5228bd5d9a/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 Z.ai

All chart data
Publisher's numbersReplica 9.0LLM Performance EvaluationZ.ai · Benchmark bar chart · 30 pointsEstimated from the imageReplica 7.7Coding Performance SWE-Bench Pro EvaluationZ.ai · Bar chart · 7 pointsEstimated from the imageReplica 7.9Coding Performance EvaluationZ.ai · Bar chart · 7 pointsPartly publisher's numbersReplica 9.2LLM Performance Bench 3.0Z.ai · Benchmark bar chart · 47 pointsPartly publisher's numbers8 LLM benchmarks: Humanity's Last Exam, SWE-bench Verified, SWE-bench Multilingual, Terminal-Bench 2.0, BrowseComp, MCP-Atlas, τ²-Bench, Vending Bench 2Z.ai · Benchmark bar chart · 57 pointsPartly publisher's numbersReplica 8.1Model Performance ComparisonZ.ai · Benchmark bar chart · 35 points

Questions people ask

How accurate are these numbers?

Part of this chart's numbers match a table the publisher wrote as text. The rest are read from the image by two independent passes and may be off.

Can I reuse this data?

The numbers describe a chart that Z.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/8f5228bd5d9a.json and /api/charts/8f5228bd5d9a.skill.md.