1. Models
  2. OpenAI
  3. Model Evaluation Scores by Benchmark
OpenAIX · Jul 18, 2024 · official

Model Evaluation Scores by Benchmark

OpenAI's grouped bar chart drew 167K views on X: 1.0x its median post and #288 of 1,162 AI chart posts we hold by views. Read Oct 13, 2026.

Model accuracy comparison across multiple evaluation benchmarks

XDataGrouped bar chartGPT-4oAll OpenAI modelsGPT-4o miniGemini FlashClaude HaikuGPT-3.5 Turbo
Published by OpenAI on X, Jul 18, 2024. Source: x.com
50/ 100

ViralChart score

Wide but thin

More views than the median post but a lower engagement rate: many saw it, few acted. Common for big accounts.

#615 of 1,162 AI chart posts we hold · #49 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 Wide but thin quadrant, at #615 of 1,162 AI chart posts.

Its save rate of 0.019% sits at the 9th percentile among AI chart posts, a bottom decile rank of #1,062 of 1,162.

It was the #2 of 2 posts from this account that day, against a same-day post at 1.3M views.

Its 0.37 views per follower is above the 0.20 median across posts with known followers, at the 61st percentile.

bottom 9%save rate

0.019% of viewers bookmarked it to come back to. The median post gets 0.076%.

bottom 9%engagement rate

0.30% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

0.37views per follower

167K views from an account with 457.2K followers.

2posts from OpenAI that day

Part of a run of 2 posts on Jul 18, 2024. This one was #2 of 2 by views that day.

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 #615 of 1,162

Views167K#288top 25%
Likes423#490top 42%
Engagement rate0.30%#1,058bottom 9%
Save rate0.019%#1,062bottom 9%

Among 74 OpenAI posts

Score #49 of 74

Views167K#35top 47%
Likes423#49bottom 34%
Engagement rate0.30%#61bottom 18%
Save rate0.019%#70bottom 6%

Growth

Our reads cover 28 hours

Views167K
Age at our read817 days
Views per day of life204views divided by days since it was posted
Gained between our reads+7views over 28 hours, about 6 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 · Jul 18, 2024

OpenAI posts grouped bar chart of model evaluation scores

The chart shows accuracy across benchmarks for GPT-4o mini, Gemini Flash, Claude Haiku, GPT-3.5 Turbo and GPT-4o.

What happened

OpenAI published a grouped bar chart on July 18, 2024, comparing model accuracy across evaluation benchmarks. It came with 1 other post from this account that day, on a GPT-4o mini pricing drop.

The numbers

The post reached 167K views, ranking #288 of 1,162 AI chart posts, against a median of 39.9K views among AI chart posts. Its score rank is #615 of 1,162 AI chart posts and #49 of 74 OpenAI posts.

The lesson

A save rate of 0.019% at the 9th percentile among AI chart posts shows that 5 models in a grouped bar chart did not travel as a reference. The chart shows printed values from 40.2% to 88.7%, but the bottom decile save rate is the measured outcome.

What it means

At #49 of 74 OpenAI posts, this chart sits below the account's own score rank pattern, and its 0.019% save rate is below the 0.076% median among AI chart posts. The 167K views against a 39.9K median show wide reach with thin engagement.

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. GPT-4o pricing reduction over time283.1K views
  2. SWE-bench Verified accuracy21.3K views
  3. Internal OpenAI Instructions following eval accuracy (hard subset)16.6K views
  4. SWE-Bench Verified Software Engineering392.1K views

Data and API

40 points read off this chart

Estimated from the image 80%
SeriesGroupValueRead
GPT-4o miniMMLU82 %printed
Gemini FlashMMLU77.9 %printed
Claude HaikuMMLU73.8 %printed
GPT-3.5 TurboMMLU69.8 %printed
GPT-4oMMLU88.7 %printed
GPT-4o miniGPQA40.2 %printed
Gemini FlashGPQA38.6 %printed
Claude HaikuGPQA35.7 %estimated
GPT-3.5 TurboGPQA30.8 %printed
GPT-4oGPQA53.6 %printed
GPT-4o miniDROP79.7 %printed
Gemini FlashDROP78.4 %printed

Showing 12 of 40. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/dac4afc9f7d6.json
GET https://viral-chart.com/api/charts/dac4afc9f7d6.json
GET https://viral-chart.com/api/charts/dac4afc9f7d6.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 dac4afc9f7d6.

See the Max planAPI docs
PathReturnsPlan
GET/api/v1/charts/dac4afc9f7d6Title, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/dac4afc9f7d6/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/dac4afc9f7d6/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/dac4afc9f7d6/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-4o

GPT-4o: GPT-4o mini pricing drop
OfficialX · OpenAIJul 18, 2024
GPT-4o mini pricing drop1.3M views · 2.5K likes
Data
GPT-4o: FrontierScience-Research accuracy across models
OfficialX · OpenAIDec 16, 2025
FrontierScience-Research accuracy across models608.9K views · 954 likes
Data
GPT-4o: FrontierScience-Olympiad accuracy across models
OfficialX · OpenAIDec 16, 2025
FrontierScience-Olympiad accuracy across models608.9K views · 954 likes
Data
GPT-4o: AIME 2025 Competition Math Accuracy
OfficialX · OpenAIOct 6, 2025
AIME 2025 Competition Math Accuracy475.6K views · 1.9K likes
Data
GPT-4o: GPQA Diamond PhD-level science questions
OfficialX · OpenAIOct 6, 2025
GPQA Diamond PhD-level science questions475.6K views · 1.9K likes
Data
GPT-4o: Internal instruction following eval
OfficialX · OpenAIDec 15, 2025
Internal instruction following eval227K views · 1K 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 Jul 18, 2024 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.