1. Chart data
  2. Z.ai
  3. Model Performance Comparison
Z.aiBenchmark bar chart · 35 points · GLM-4

Model Performance Comparison

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

Partly publisher's numbers 87%GLM-4All Z.ai modelsAll chart data
Chart by Z.ai. Source: github.com

Our replica

Look-alike score 8.1 of 10
The original, Z.ai
Our replica. Look-alike score 8.1 of 10Swipe sideways to read the labels.

Drawn by us in your browser from the numbers below, in the same layout, palette and label style as the original. Values marked with ~ in the table are estimates. A replica needs 7 of 10 from our judges to be shown.

The numbers

First 10 of 35 points are free
GroupSeriesValueSourceConf.
IFEval 指令遵循GLM-4-32B-041487.6Publisher1.00
IFEval 指令遵循Qwen2.5-Max85.6Publisher1.00
IFEval 指令遵循GPT-4o-112081.9Publisher1.00
IFEval 指令遵循DeepSeek-V3-032483.4Publisher1.00
IFEval 指令遵循DeepSeek-R184.3Publisher1.00
BFCL-v3 综合工具调用GLM-4-32B-041469.6Estimate0.97
BFCL-v3 综合工具调用Qwen2.5-Max50.9Estimate0.97
BFCL-v3 综合工具调用GPT-4o-112069.6Estimate0.30
BFCL-v3 综合工具调用DeepSeek-V3-032466.2Estimate0.30
BFCL-v3 综合工具调用DeepSeek-R157.5Estimate0.30

Max data, free with your email for now

See all 35 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

BFCL-v3 多轮工具调用GLM-4-32B-041441.5Estimate0.97
BFCL-v3 多轮工具调用Qwen2.5-Max30.5Estimate0.97
BFCL-v3 多轮工具调用GPT-4o-112041Estimate0.97
BFCL-v3 多轮工具调用DeepSeek-V3-032435.8Estimate0.97
BFCL-v3 多轮工具调用DeepSeek-R112.4Estimate0.97
TAU-Bench 智能体工具调用GLM-4-32B-041468.7Estimate0.97
TAU-Bench 智能体工具调用Qwen2.5-Max58.3Estimate0.97
TAU-Bench 智能体工具调用GPT-4o-112062.8Estimate0.97
TAU-Bench 智能体工具调用DeepSeek-V3-032460.7Estimate0.97
TAU-Bench 智能体工具调用DeepSeek-R133Estimate0.30
TAU-Bench 智能体工具调用GLM-4-32B-041451.2Estimate0.97
TAU-Bench 智能体工具调用Qwen2.5-Max22Estimate0.97
TAU-Bench 智能体工具调用GPT-4o-112046Estimate0.30
TAU-Bench 智能体工具调用DeepSeek-V3-032432.4Estimate0.97
TAU-Bench 智能体工具调用DeepSeek-R137.3Estimate0.30
SimpleQA 搜索问答GLM-4-32B-041488.1Publisher1.00
SimpleQA 搜索问答Qwen2.5-Max79Publisher1.00
SimpleQA 搜索问答GPT-4o-112082.8Publisher1.00
SimpleQA 搜索问答DeepSeek-V3-032482.6Publisher1.00
SimpleQA 搜索问答DeepSeek-R183.9Publisher1.00
HotpotQA 搜索问答GLM-4-32B-041463.8Publisher1.00
HotpotQA 搜索问答Qwen2.5-Max52.8Publisher1.00
HotpotQA 搜索问答GPT-4o-112063.9Publisher1.00
HotpotQA 搜索问答DeepSeek-V3-032454.6Publisher1.00
HotpotQA 搜索问答DeepSeek-R163.1Publisher1.00
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 94ecfc033194.

See the Max planAPI docs
PathReturnsPlan
GET/api/v1/charts/94ecfc033194Title, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/94ecfc033194/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/94ecfc033194/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/94ecfc033194/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

Start from our replica of this chart, or from a simplified form. Either way your numbers start from this chart's real data.

More data from Z.ai

All chart data
Publisher's numbersReplica 9.0LLM Performance EvaluationZ.ai · Benchmark bar chart · 30 pointsPartly publisher's numbersLLM Benchmarks: Terminal Bench 2.1, DeepSWE v1.1, Agents' Last Exam, AutomationBench v1.0.6, HLE w/ Tools, GDPVal-AA v2Z.ai · Benchmark bar chart · 33 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 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/94ecfc033194.json and /api/charts/94ecfc033194.skill.md.