Models
OpenAI
GPT-OSS MoE Training Performance

@SemiAnalysis_X · Sep 26, 2026

GPT-OSS MoE Training Performance

@SemiAnalysis_'s bar chart drew 14.8K views on X: 0.4x @semianalysis_'s median post and #762 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

GPT-OSS MoE training performance across providers

XData Bar chart gpt-oss All OpenAI modelsNebiusGMIAzureFirmus

@SemiAnalysis_: GPT-OSS MoE Training Performance — Published by @SemiAnalysis_ on X, Sep 26, 2026. Source: x.com

16/ 100

ViralChart score

Quiet

Fewer views and a lower engagement rate than the median post.

#1,096 of 1,162 AI chart posts we hold · #22 of 24 @semianalysis_ 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 Quiet quadrant, with a score rank of #1,096 of 1,162 AI chart posts.

Its 0.081% engagement rate sits at 2nd percentile among AI chart posts, 0.11x the 0.73% median.

The score of 16 ranks #1,096 of 1,162 AI chart posts and #22 of 24 @SemiAnalysis_ posts.

At 14.8K views it reaches 0.37x the 40.3K company median, #20 of 24 @SemiAnalysis_ posts.

bottom 2%engagement rate

0.08% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

bottom 5%save rate

0.007% of viewers bookmarked it to come back to. The median post gets 0.076%.

0.4x@semianalysis_'s median post

14.8K views, where @semianalysis_'s typical post gets 40.3K.

0.6xthe median bar chart post

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

Public X numbers from our read on Oct 12, 2026. Peers: 1,162 AI chart posts we hold and 24 from @semianalysis_.

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 #1,096 of 1,162

Views	14.8K	#762	bottom 34%
Likes	9	#1,125	bottom 3%
Engagement rate	0.08%	#1,145	bottom 2%
Save rate	0.007%	#1,104	bottom 5%

Among 24 @semianalysis_ posts

Score #22 of 24

Views	14.8K	#20	bottom 19%
Likes	9	#23	bottom 6%
Engagement rate	0.08%	#24	bottom 2%
Save rate	0.007%	#23	bottom 6%

Growth

One read so far

Views14.8K

Age at our read16 days

Views per day of life928views 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.

@semianalysis_'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 26, 2026

@SemiAnalysis_ GPT-OSS MoE training performance bar chart

A 4-model bar chart on GPT-OSS MoE training performance drew 14.8K views and a 0.081% engagement rate.

What happened

@SemiAnalysis_ posted a bar chart on GPT-OSS MoE training performance on September 26, 2026. It was the account's only post that day.

The numbers

It reached 14.8K views, #762 of 1,162 AI chart posts, against a 39.9K median among AI chart posts. Its score of 16 ranked #1,096 of 1,162 AI chart posts.

The lesson

A 4-model bar chart at 0.081% engagement, 0.11x the 0.73% AI chart median, shows a clean comparison table is not what readers keep to cite. The 0.007% save rate sits with it.

What it means

At #22 of 24 @SemiAnalysis_ posts and 0.37x the 40.3K company median, this chart post trails the account's own output. The 14.8K views against the 39.9K AI chart median leave it wide but thin.

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

Updates: what @semianalysis_ posted next

Data and API

5 points read off this chart

Estimated from the image 93%

Series	Group	Value	Read
Nebius	Nebius (slurm) 16 GPU	3600 tokens/sec/GPU	printed
Azure	Azure (slurm) 16 GPU	3250 tokens/sec/GPU	printed
GMI	GMI (slurm) 16 GPU	3350 tokens/sec/GPU	printed
GMI	GMI (k8s) 16 GPU	1600 tokens/sec/GPU	printed
Firmus	Firmus (k8s) 16 GPU	1350 tokens/sec/GPU	printed

Max plan · API

GET https://viral-chart.com/api/posts/af79bfdb6aac.json
GET https://viral-chart.com/api/charts/af79bfdb6aac.json
GET https://viral-chart.com/api/charts/af79bfdb6aac.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 af79bfdb6aac.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/af79bfdb6aac`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/af79bfdb6aac/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/af79bfdb6aac/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/af79bfdb6aac/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-oss

gpt-oss: Frontier Language Model Intelligence by Country

X · @ArtificialAnlysNov 11, 2025

Frontier Language Model Intelligence by Country59.3K views · 534 likes

Data

gpt-oss: Output Tokens Used to Run Evaluations in Artificial

X · @ArtificialAnlysAug 6, 2025

Output Tokens Used to Run Evaluations in Artificial7.3K views · 54 likes

Data

X · @ArtificialAnlysAug 6, 2025

Cost to Run AI Evaluations7.3K views · 54 likes

Data

gpt-oss: Artificial Analysis Intelligence vs Output Tokens

X · @ArtificialAnlysAug 6, 2025

Artificial Analysis Intelligence vs Output Tokens7.3K views · 54 likes

Data

gpt-oss: Intelligence vs. Total Parameters

X · @ArtificialAnlysMar 20, 2026

Intelligence vs. Total Parameters5.2K views · 27 likes

Data

OpenRouter · openrouter

Decline of DeepSeek's Dominance in OSS Token Market

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?

@SemiAnalysis_ published it on Sep 26, 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.