1. Models
  2. OpenAI
  3. OSWorld 2.0 offline set: Score vs Cost
OpenAIX · Sep 29, 2026 · official

OSWorld 2.0 offline set: Score vs Cost

OpenAI's line chart drew 208.5K views on X: 1.3x its median post and #256 of 1,162 AI chart posts we hold by views. Read Oct 13, 2026.

Performance and cost comparison of GPT-6 models

XDataLine chartGPT-6All OpenAI modelsGPT-6 SolGPT-6 AstraGPT-6.1 Sol
Published by OpenAI on X, Sep 29, 2026. Source: x.com
70/ 100

ViralChart score

Reached and resonated

More views and a higher engagement rate than the median post: it travelled and people acted on it.

#221 of 1,162 AI chart posts we hold · #15 of 74 OpenAI posts. Score = views 40%, likes 30%, engagement rate 15%, save rate 15%, each as a percentile of every AI chart post we hold.

Our read

The post sits in the Reached and resonated quadrant at #221 of 1,162 AI chart posts.

Its score of 70 ranks #221 of 1,162 AI chart posts, above the field.

At 0.038 views per follower against a 0.20 median, it sits at 0.19x that median.

It ranked #1 of 3 posts from this account that day by views.

0.04views per follower

208.5K views from an account with 5.4M followers.

3charts in this one post

The numbers belong to the post, so every chart in it shares them and it is ranked once.

3posts from OpenAI that day

Part of a run of 3 posts on Sep 29, 2026. This one was #1 of 3 by views that day.

2.8xthe median line chart post

Across 68 line chart posts we hold, the median gets 73.7K views.

Public X numbers from our read on Oct 13, 2026. Peers: 1,162 AI chart posts we hold and 74 from OpenAI.

Where it sits

Reach against resonance

Each dot is a post. Right is more views, up is a higher engagement rate. The lines are the medians, so the four corners are the four kinds of post.

Among 1,162 AI chart posts we hold

Score #221 of 1,162

Views208.5K#256top 22%
Likes1.4K#213top 18%
Engagement rate0.77%#545top 47%
Save rate0.062%#701bottom 40%

Among 74 OpenAI posts

Score #15 of 74

Views208.5K#34top 45%
Likes1.4K#22top 29%
Engagement rate0.77%#20top 26%
Save rate0.062%#24top 32%

Growth

Our reads cover 26 hours

Views208.5K
Age at our read14 days
Views per day of life14.9Kviews divided by days since it was posted
Gained between our reads+771views over 26 hours, about 705 a day now

Dots are our reads. The dotted line from the day it was posted to our first read is a gap, not data.

OpenAI's posts over time

Every post from this account we hold, by date and views. This one is marked; the line is the running median of the last 10.

News · Sep 29, 2026

OpenAI posts OSWorld 2.0 offline set: Score vs Cost

A line chart on GPT-6 model performance and cost drew 208K views and a 0.77% engagement rate.

What happened

OpenAI published a line chart on September 29, 2026, comparing score against cost for GPT-6 models. It came with 3 charts in the post, including Model Cost vs Score and DeepSWE Model Performance vs Cost, and 2 other posts from the account that day.

The numbers

The post reached 208K views, ranking #256 of 1,162 AI chart posts. Its score of 70 ranked #221 of 1,162 AI chart posts and #15 of 74 OpenAI posts.

The lesson

With 3 models shown in a line chart, the post drew 208K views and a 0.77% engagement rate. The 0.062% save rate against that engagement shows saves lagged likes.

What it means

At #15 of 74 OpenAI posts, this chart sits in the account's top tier by score. Its 0.038 views per follower against a 0.20 median marks a gap to the median across posts with known followers.

Written by ViralChart from public numbers read on Oct 13, 2026. Every number is checked against our data before it is shown.

Updates: what OpenAI posted next

  1. Factual error rate vs cost on difficult prompts20.9K views

Data and API

15 points read off this chart

Estimated from the image 67%
SeriesGroupValueRead
GPT-6.1 Sol59 %estimated
GPT-6.1 Sol66 %estimated
GPT-6.1 Sol69 %estimated
GPT-6.1 Sol71 %estimated
GPT-6 Sol44 %estimated
GPT-6 Sol54 %estimated
GPT-6 Sol58 %estimated
GPT-6 Sol60 %estimated
GPT-6 Sol62 %estimated
GPT-6 Astra62 %estimated
GPT-6 Astra69 %estimated
GPT-6 Astra70 %estimated

Showing 12 of 15. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/d918c4b6b211.json
GET https://viral-chart.com/api/charts/d918c4b6b211.json
GET https://viral-chart.com/api/charts/d918c4b6b211.skill.md
Make one like thisOpen the post JSONChart data JSONSkill fileAPI docs

Static files in this prototype. The post JSON holds the public numbers, ranks, score, quadrant, our reads and, when checked, our copy.

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 d918c4b6b211.

See the Max planAPI docs
PathReturnsPlan
GET/api/v1/charts/d918c4b6b211Title, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/d918c4b6b211/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/d918c4b6b211/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/d918c4b6b211/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.

More charts about GPT-6

GPT-6: Model Cost vs Score
OfficialX · OpenAISep 29, 2026
Model Cost vs Score208.5K views · 1.4K likes
Data
GPT-6: DeepSWE Model Performance vs Cost
OfficialX · OpenAISep 29, 2026
DeepSWE Model Performance vs Cost208.5K views · 1.4K likes
Data
GPT-6: Factual error rate vs cost on difficult prompts
OfficialX · OpenAISep 29, 2026
Factual error rate vs cost on difficult prompts20.9K views · 118 likes
Data
GPT-6: Prompt caching usage
OfficialBlog · OpenAIOct 7, 2026
Prompt caching usage
GPT-6: Code GPT-6 Astra (Max) Ranked #1
X · @arenaSep 5, 2026
Code GPT-6 Astra (Max) Ranked #1805.6K views · 4.2K likes
Data
GPT-6: Intelligence Index vs Output Tokens
X · @ArtificialAnlysSep 3, 2026
Intelligence Index vs Output Tokens316.2K views · 323 likes
Data

More from OpenAI

OpenAI line chart: Output tokens by department2.3x
OpenAI·Jun 2026
Output tokens by department
1.3M views5.4K likes0.5% eng.
Data
OpenAI annotated chart: Research paper benchmarking2.9x
OpenAI·Apr 2025
Research paper benchmarking
1.1M views7K likes0.8% eng.
OpenAI bar chart: AI model performance2.0x
OpenAI·Sep 2026
AI model performance
999.9K views4.8K likes0.6% eng.
Data
ChatGPT: Artificial Analysis Intelligence Index v4.1
OfficialX · OpenAIJul 30, 2026
Artificial Analysis Intelligence Index v4.121M views · 19.5K likes
Data
ChatGPT: AI Model Benchmark Comparison
OfficialX · OpenAIMar 5, 2026
AI Model Benchmark Comparison7.2M views · 23.2K likes
Data
ChatGPT: GPT4 Turbo Benchmark Comparison
OfficialX · OpenAIApr 12, 2024
GPT4 Turbo Benchmark Comparison6.4M views · 6.7K likes
Data
GPT-5.6: AI Model Benchmark Comparison
OfficialX · OpenAISep 3, 2026
AI Model Benchmark Comparison5.4M views · 10.3K likes
Data
GPT-5: AI Model Benchmark Comparison
OfficialX · OpenAIDec 11, 2025
AI Model Benchmark Comparison2M views · 3.8K likes
Data
GPT-5.6: TerminalBench 2.1 AI Model Scores
OfficialX · OpenAIJun 26, 2026
TerminalBench 2.1 AI Model Scores1.9M views · 3.9K likes
Data

Questions people ask

Where does this chart come from?

OpenAI published it on Sep 29, 2026 on X (x.com). We keep it here, with the publisher and date credited as text, so you can study it without leaving.

Can I make a chart like this?

Use the format, not the picture. Open its data page and use Make one like this: it starts from this chart's numbers and takes yours.