Models
OpenAI
SWE-Bench Verified Accuracy vs Thinking Tokens

OpenAIX · Nov 19, 2025 · official

SWE-Bench Verified Accuracy vs Thinking Tokens

OpenAI's line chart drew 89K views on X: 0.6x its median post and #407 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

Accuracy increases with thinking tokens for GPT-5.1 models

XData Line chart Codex All OpenAI modelsGPT-5.1-CodexGPT-5.1-Codex-Max

OpenAI: SWE-Bench Verified Accuracy vs Thinking Tokens — Published by OpenAI on X, Nov 19, 2025. Source: x.com

43/ 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.

#714 of 1,162 AI chart posts we hold · #62 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 #714 of 1,162 AI chart posts.

Its 0.27% engagement rate sits at the 8th percentile among AI chart posts, in the bottom decile.

It ranked #1 of 2 posts from this account that day by views.

Its 89K views are 0.55x OpenAI's 162K median, ranking #48 of 74 OpenAI posts.

0.19views per follower

89K views from an account with 457.2K followers.

bottom 8%engagement rate

0.27% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

bottom 12%save rate

0.024% of viewers bookmarked it to come back to. The median post gets 0.076%.

2posts from OpenAI that day

Part of a run of 2 posts on Nov 19, 2025. This one was #1 of 2 by views that day.

Public X numbers from our read on Oct 12, 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 #714 of 1,162

Views	89K	#407	top 35%
Likes	214	#632	bottom 46%
Engagement rate	0.27%	#1,073	bottom 8%
Save rate	0.024%	#1,026	bottom 12%

Among 74 OpenAI posts

Score #62 of 74

Views	89K	#48	bottom 36%
Likes	214	#58	bottom 22%
Engagement rate	0.27%	#64	bottom 14%
Save rate	0.024%	#63	bottom 16%

Growth

One read so far

Views89K

Age at our read327 days

Views per day of life272views divided by days since it was posted

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 · Nov 19, 2025

OpenAI posts SWE-Bench Verified accuracy vs thinking tokens chart

The line chart shows accuracy against thinking tokens for GPT-5.1 models, posted on November 19, 2025.

What happened

OpenAI published a line chart on November 19, 2025, showing SWE-Bench Verified accuracy versus thinking tokens. It came with 1 other post from this account that day, on SWE-Lancer IC SWE Accuracy.

The numbers

The post reached 89K views, ranking #407 of 1,162 AI chart posts by views. Its score rank is #714 of 1,162 AI chart posts.

The lesson

At 0.27% engagement against a 0.73% median among AI chart posts, this line chart landed in the bottom decile. A 2-model line chart drew 89K views but a save rate of 0.024%.

What it means

At #62 of 74 OpenAI posts by score, this chart trails the account's own output. The 0.55x gap to OpenAI's 162K median views shows the reach shortfall against company posts.

Written by ViralChart from public numbers read on Oct 12, 2026. Every number is checked against our data before it is shown.

Updates: what OpenAI posted next

Data and API

7 points read off this chart

Estimated from the image 44%

Series	Group	Value	Read
GPT-5.1-Codex	low	70.5 %	estimated
GPT-5.1-Codex	medium	72.5 %	estimated
GPT-5.1-Codex	high	73.5 %	estimated
GPT-5.1-Codex-Max	low	70.5 %	estimated
GPT-5.1-Codex-Max	medium	76.8 %	estimated
GPT-5.1-Codex-Max	xhigh	77.8 %	estimated
GPT-5.1-Codex-Max	high	76.8 %	estimated

Max plan · API

GET https://viral-chart.com/api/posts/fb022dd22d31.json
GET https://viral-chart.com/api/charts/fb022dd22d31.json
GET https://viral-chart.com/api/charts/fb022dd22d31.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 fb022dd22d31.

Approximate values. Our two readings of this chart agreed only in part (confidence 0.44 of 1), so check the original before you quote a number. The API marks it lowConfidence, and ?min_confidence=0.5 leaves it out.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/fb022dd22d31`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/fb022dd22d31/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/fb022dd22d31/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/fb022dd22d31/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 Codex

OfficialX · OpenAIApr 23, 2026

AI Model Benchmark Comparison1.7M views · 4.9K likes

Data

Codex: Non-developer active users growth

OfficialX · OpenAIJun 25, 2026

Non-developer active users growth1.3M views · 5.4K likes

Data

Codex: Occupation vs. work tokens done with Codex

OfficialX · OpenAIJun 25, 2026

Occupation vs. work tokens done with Codex1.3M views · 5.4K likes

Data

OfficialX · OpenAIJun 25, 2026

Developer App Usage Growth1.3M views · 5.4K likes

Data

Codex: Recent open weight models on long-horizon cyber ranges

OfficialX · OpenAIJul 17, 2026

Recent open weight models on long-horizon cyber ranges767.7K views · 3.9K likes

Data

OfficialX · OpenAISep 27, 2026

Visual Grounding Performance Fix704.9K views · 6.1K 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 Nov 19, 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.