FrontierMath Tier 4 accuracy
Epoch AI's benchmark bar chart drew 266.9K views on X: 3.9x its typical post and #15 of 97 Epoch AI charts we track by views. Read Oct 10, 2026.
We manually evaluated three compute-intensive model settings on our extremely hard math benchmark. FrontierMath Tier 4: Battle Royale!
Why it spread
This chart post spread because it landed at launch timing with an independent author, and the account's 543 likes were far above its typical 114, while 266,890 views, 66 reposts, 25 quotes and 100 saves showed strong reach and sharing.
What worked
- The post framed a hard benchmark as a close race, with GPT-5 Pro at 13% edging out Gemini 2.5 Deep Think by a single problem, which made the result feel dramatic but honest.
- The chart was branded, showed a source line, and used a benchmark-bars form that made a high-compute model comparison easy to read at a glance.
- The account posted at launch timing as an independent author, and the topic sat in the ai-bench category, which helped it travel beyond the account's usual audience.
What to borrow
We could use the same benchmark-bars form and race framing for our own data by showing a close result between top models, labeling the source clearly, and timing the post to a launch moment.
Careful
Do not over-read the single-problem gap as a real quality difference, since the post itself calls it not statistically significant, and do not assume the same numbers will repeat for our account.
Written by our analysis model from the measured numbers above, not by Epoch AI.
Make it yours
Your numbers, in this bar chart.
Starts from the real numbers of "FrontierMath Tier 4 accuracy for high-compute model settings" by Epoch AI. 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 45a4b6d1d6f4.
Approximate values. Our two readings of this chart agreed only in part (confidence 0.30 of 1), so check the original before you quote a number. The API marks it lowConfidence, and ?min_confidence=0.5 leaves it out.
| Path | Returns | Plan | |
|---|---|---|---|
| GET | /api/v1/charts/45a4b6d1d6f4 | Title, publisher, date, form, point count; with a Max key, the data link | Open |
| GET | /api/v1/charts/45a4b6d1d6f4/data | Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV | Max |
| GET | /api/v1/charts/45a4b6d1d6f4/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/45a4b6d1d6f4/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 Epoch AI
All 97
Other giants using a benchmark bar chart
All 136
Questions people ask
How far did Epoch AI's "FrontierMath Tier 4 accuracy" chart travel?
266,890 views, 543 likes, 66 reposts and 100 saves on X, read Oct 10, 2026. A normal post from @EpochAIResearch gets about 68.2K views.
What kind of chart is it?
A benchmark bar chart. Model accuracy comparison for high-compute models.
Can I use Epoch AI's chart?
Use the format, not the picture. The chart, logo and design belong to Epoch AI. ViralChart redraws the chart type with your numbers and words, and credits the original publisher.