- Giants
- Artificial Analysis
- AI model benchmark scores
AI model benchmark scores
Artificial Analysis's bar chart drew 127.4K views on X: 11x @artificialanlys's median post and #340 of 1,162 AI chart posts we hold by views. Read Oct 10, 2026.
Llama 4 independent evals: Maverick (402B total, 17B active) beats Claude 3.7 Sonnet, trails DeepSeek V3 but more efficient; Scout (109B total, 17B active) in-line with GPT-4o mini, ahead of Mistral Small 3.1
Why it spread
The post spread because an independent author published benchmark results for Llama 4 models, drawing 621 likes, 86 reposts, 32 quotes, 212 saves and 127,389 views, with a quote rate in the top quarter and source reach in the top quarter.
What worked
- The post leads with a clear comparison claim: Maverick beats Claude 3.7 Sonnet, trails DeepSeek V3 but is more efficient, while Scout is in line with GPT-4o mini and ahead of Mistral Small 3.1.
- It gives concrete model sizes and scores, naming Maverick at 402B total and 17B active, Scout at 109B total and 17B active, and stating scores of 36 and 49.
- It comes from an independent author, which the facts list as a main reason, and it earned many quotes, another listed main reason.
What to borrow
We could publish our own chart as calmer independent evaluation, pairing a plain bar ranking of models by benchmark score with a short text claim that names the models we beat, trail or match, and states the total and active parameter counts and the scores.
Careful
Do not copy the low design polish or low self labelling, and do not over read the missing source line, the null points and comments, or the absent account typical likes and times the account normal, since those are not measured here.
Written by our analysis model from the measured numbers above, not by Artificial Analysis.
Make it yours
Your numbers, in this bar chart.
Starts from the real numbers of "Artificial Intelligence Index incorporates 7 evaluations: MMLU-Pro, GPQA Diamond, Humanity" by artificial-analysis. Replace every number with yours before you post. Make one like this, step by step
Free pictures carry a small "Made with ViralChart" line. That line is how other people find us.
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 cbc86e8d2ffa.
| Path | Returns | Plan | |
|---|---|---|---|
| GET | /api/v1/charts/cbc86e8d2ffa | Title, publisher, date, form, point count; with a Max key, the data link | Open |
| GET | /api/v1/charts/cbc86e8d2ffa/data | Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV | Max |
| GET | /api/v1/charts/cbc86e8d2ffa/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 |
curl -s https://viral-chart.com/api/v1/charts/cbc86e8d2ffa/data \
-H "Authorization: Bearer $VIRALCHART_KEY"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 from Artificial Analysis
All 123
Other giants using a bar chart
All 152
Questions people ask
How far did Artificial Analysis's "AI model benchmark scores" chart travel?
127,389 views, 621 likes, 86 reposts and 212 saves on X, read Oct 10, 2026. A normal post from @ArtificialAnlys gets about 54.2K views.
What kind of chart is it?
A bar chart. AI models ranked by benchmark evaluation scores.
Can I use Artificial Analysis's chart?
Use the format, not the picture. The chart, logo and design belong to Artificial Analysis. ViralChart redraws the chart type with your numbers and words, and credits the original publisher.