Models
OpenAI
Internal hallucination with noise eval

OpenAIX · Dec 15, 2025 · official

Internal hallucination with noise eval

OpenAI's bar chart drew 227K views on X: 1.4x its median post and #241 of 1,162 AI chart posts we hold by views. Read Oct 13, 2026.

WER comparison for hallucination with noise

XData Bar chart GPT-4o All OpenAI modelsgpt-4o-mini-transcribe-2025-12-15gpt-4o-mini-transcribegpt-4o-transcribewhisper-1

OpenAI: Internal hallucination with noise eval — Published by OpenAI on X, Dec 15, 2025. Source: x.com

71/ 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.

#200 of 1,162 AI chart posts we hold · #13 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, with a score rank of #200 of 1,162 AI chart posts.

Its score of 71 ranks #200 of 1,162 AI chart posts and #13 of 74 OpenAI posts.

The post carries 3 charts, and every chart in the post shares the post's numbers.

Its save rate of 0.12% sits at the 72nd percentile among AI chart posts, 1.6x the 0.076% median.

8.9xthe median bar chart post

Across 241 bar chart posts we hold, the median gets 25.6K views.

3charts in this one post

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

top 28%save rate

0.123% of viewers bookmarked it to come back to. The median post gets 0.076%.

0.50views per follower

227K views from an account with 457.2K followers.

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 #200 of 1,162

Views	227K	#241	top 21%
Likes	1K	#264	top 23%
Engagement rate	0.54%	#789	bottom 32%
Save rate	0.123%	#322	top 28%

Among 74 OpenAI posts

Score #13 of 74

Views	227K	#29	top 39%
Likes	1K	#30	top 40%
Engagement rate	0.54%	#37	top 49%
Save rate	0.123%	#6	top 7%

Growth

Our reads cover 27 hours

Views227K

Age at our read302 days

Views per day of life752views divided by days since it was posted

Gained between our reads+1views over 27 hours, about 1 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 · Dec 15, 2025

OpenAI posts hallucination with noise WER bar chart

A bar chart on hallucination with noise WER drew 227K views and a 0.54% engagement rate, landing in the Wide but thin quadrant.

What happened

OpenAI posted a bar chart on December 15, 2025, comparing hallucination with noise WER. The post carried 合法性 charts, including Common Voice WER comparison and Internal instruction following eval, and it was the account's only post that day.

The numbers

The post reached 227K views, ranking #241 of 1,162 AI chart posts, against a median of 39.9K. Its score of 71 ranked #200 of 1,162 AI chart posts and #13 of 74 OpenAI posts.

The lesson

A save rate of 0.12%, 1.6x the 0.076% median among AI chart posts, shows readers kept this 4-model comparison at a higher rate than the median. The 3 charts in the post each share the post's numbers, so the save rate applies to the whole set.

What it means

At #13 of 74 OpenAI posts, this chart post sits above the account's own median rank position. Its 0.54% engagement rate falls below the AI chart median, so the 227K views did not carry a matching engagement rate.

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

Data and API

4 points read off this chart

Estimated from the image 97%

Group	Value	Read
gpt-4o-mini-transcribe-2025-12-15	0.07	printed
gpt-4o-mini-transcribe	0.23	printed
gpt-4o-transcribe	0.21	printed
whisper-1	0.61	printed

Max plan · API

GET https://viral-chart.com/api/posts/c239e5dbf8d6.json
GET https://viral-chart.com/api/charts/c239e5dbf8d6.json
GET https://viral-chart.com/api/charts/c239e5dbf8d6.skill.md

Make one like this Open the post JSON Chart data JSON Skill file API 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 c239e5dbf8d6.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/c239e5dbf8d6`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/c239e5dbf8d6/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/c239e5dbf8d6/render?view=1`	The draw-only view this page uses	Open
POST	`/mcp`	Tool get_chart_data with this id, for Claude, Cursor and other agents	Max

curlMax

curl -s https://viral-chart.com/api/v1/charts/c239e5dbf8d6/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

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 department

2.3x

OpenAI·Jun 2026

Output tokens by department

1.3M views5.4K likes0.5% eng.

Data

OpenAI annotated chart: Research paper benchmarking

2.9x

OpenAI·Apr 2025

Research paper benchmarking

1.1M views7K likes0.8% eng.

2.0x

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

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

OfficialX · OpenAISep 3, 2026

AI Model Benchmark Comparison5.4M views · 10.3K likes

Data

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 Dec 15, 2025 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.