- Chart data
- Anthropic
- Sonnet 4.6
Sonnet 4.6
The numbers behind a chart Anthropic published, redrawn natively. Check the original, study the data, then make your own.
Our replica
Look-alike score 8.0 of 10Drawn by us in your browser from the numbers below, in the same layout, palette and label style as the original. Values marked with ~ in the table are estimates. A replica needs 7 of 10 from our judges to be shown.
The numbers
First 10 of 83 points are free| Group | Series | Value | Source | Conf. |
|---|---|---|---|---|
| Agentic terminal coding Terminal-Bench 2.0 | Sonnet 4.6 | 59.1 | Estimate | 0.97 |
| Agentic terminal coding Terminal-Bench 2.0 | Sonnet 4.5 | 51 | Estimate | 0.97 |
| Agentic terminal coding Terminal-Bench 2.0 | Opus 4.6 | 65.4 | Estimate | 0.97 |
| Agentic terminal coding Terminal-Bench 2.0 | Opus 4.5 | 59.8 | Estimate | 0.97 |
| Agentic terminal coding Terminal-Bench 2.0 | Gemini 3 Pro | 56.2 | Estimate | 0.97 |
| Agentic terminal coding Terminal-Bench 2.0 | GPT-5.2 (all models) | 64.7 | Estimate | 0.97 |
| Agentic coding SWE-bench Verified | Sonnet 4.6 | 79.6 | Estimate | 0.97 |
| Agentic coding SWE-bench Verified | Sonnet 4.5 | 77.2 | Estimate | 0.97 |
| Agentic coding SWE-bench Verified | Opus 4.6 | 80.8 | Estimate | 0.97 |
| Agentic coding SWE-bench Verified | Opus 4.5 | 80.9 | Estimate | 0.97 |
Max data, free with your email for now
See all 83 points and download the files
The full table, the JSON, a CSV and the agent skill file for this chart. These are Max in the plan; while this is a prototype your email unlocks them.
Unlocks all 35 giants. One email a week, leave any time. What you get · Log in
| Agentic coding SWE-bench Verified | Gemini 3 Pro | 78 | Estimate | 0.97 |
|---|---|---|---|---|
| Agentic coding SWE-bench Verified | GPT-5.2 (all models) | 80 | Estimate | 0.97 |
| Agentic computer use OSWorld-Verified | Sonnet 4.6 | 72.5 | Estimate | 0.97 |
| Agentic computer use OSWorld-Verified | Sonnet 4.5 | 61.4 | Estimate | 0.97 |
| Agentic computer use OSWorld-Verified | Opus 4.6 | 72.7 | Estimate | 0.97 |
| Agentic computer use OSWorld-Verified | Opus 4.5 | 66.3 | Estimate | 0.97 |
| Agentic computer use OSWorld-Verified | GPT-5.2 (all models) | 38.2 | Estimate | 0.97 |
| Agentic tool use τ2-bench | Sonnet 4.6 | 91.7 | Estimate | 0.30 |
| Agentic tool use τ2-bench | Sonnet 4.5 | 86.2 | Estimate | 0.30 |
| Agentic tool use τ2-bench | Opus 4.6 | 91.9 | Estimate | 0.30 |
| Agentic tool use τ2-bench | Opus 4.5 | 88.9 | Estimate | 0.30 |
| Agentic tool use τ2-bench | Gemini 3 Pro | 85.3 | Estimate | 0.30 |
| Agentic tool use τ2-bench | GPT-5.2 (all models) | 82 | Estimate | 0.30 |
| Scaled tool use MCP-A2B | Sonnet 4.6 | 61.3 | Estimate | 0.50 |
| Scaled tool use MCP-A2B | Sonnet 4.5 | 43.8 | Estimate | 0.50 |
| Scaled tool use MCP-A2B | Opus 4.6 | 59.5 | Estimate | 0.50 |
| Scaled tool use MCP-A2B | Opus 4.5 | 62.3 | Estimate | 0.50 |
| Scaled tool use MCP-A2B | Gemini 3 Pro | 54.1 | Estimate | 0.50 |
| Scaled tool use MCP-A2B | GPT-5.2 (all models) | 60.6 | Estimate | 0.50 |
| Agentic search BrowseComp | Sonnet 4.6 | 74.7 | Estimate | 0.97 |
| Agentic search BrowseComp | Sonnet 4.5 | 43.9 | Estimate | 0.97 |
| Agentic search BrowseComp | Opus 4.6 | 84 | Estimate | 0.97 |
| Agentic search BrowseComp | Opus 4.5 | 67.8 | Estimate | 0.97 |
| Agentic search BrowseComp | Gemini 3 Pro | 59.2 | Estimate | 0.97 |
| Agentic search BrowseComp | GPT-5.2 (all models) | 77.9 | Estimate | 0.97 |
| Multidisciplinary reasoning Humanity's Last Exam (HLE) | Sonnet 4.6 | 33.2 | Estimate | 0.97 |
| Multidisciplinary reasoning Humanity's Last Exam (HLE) | Sonnet 4.5 | 17.7 | Estimate | 0.30 |
| Multidisciplinary reasoning Humanity's Last Exam (HLE) | Opus 4.6 | 40 | Estimate | 0.97 |
| Multidisciplinary reasoning Humanity's Last Exam (HLE) | Opus 4.5 | 30.8 | Estimate | 0.97 |
| Multidisciplinary reasoning Humanity's Last Exam (HLE) | Gemini 3 Pro | 37.5 | Estimate | 0.97 |
| Multidisciplinary reasoning Humanity's Last Exam (HLE) | GPT-5.2 (all models) | 36.6 | Estimate | 0.97 |
| Agentic financial analysis Finance Agent v1.1 | Sonnet 4.6 | 63.3 | Estimate | 0.97 |
| Agentic financial analysis Finance Agent v1.1 | Sonnet 4.5 | 54.5 | Estimate | 0.97 |
| Agentic financial analysis Finance Agent v1.1 | Opus 4.6 | 60.1 | Estimate | 0.97 |
| Agentic financial analysis Finance Agent v1.1 | Opus 4.5 | 58.8 | Estimate | 0.97 |
| Agentic financial analysis Finance Agent v1.1 | Gemini 3 Pro | 55.2 | Estimate | 0.30 |
| Agentic financial analysis Finance Agent v1.1 | GPT-5.2 (all models) | 59 | Estimate | 0.97 |
| Office tasks solving DOPPLER-AIA-BIG | Sonnet 4.6 | 1633 | Estimate | 0.97 |
| Office tasks solving DOPPLER-AIA-BIG | Sonnet 4.5 | 1276 | Estimate | 0.97 |
| Office tasks solving DOPPLER-AIA-BIG | Opus 4.6 | 1606 | Estimate | 0.97 |
| Office tasks solving DOPPLER-AIA-BIG | Opus 4.5 | 1416 | Estimate | 0.97 |
| Office tasks solving DOPPLER-AIA-BIG | Gemini 3 Pro | 1201 | Estimate | 0.97 |
| Office tasks solving DOPPLER-AIA-BIG | GPT-5.2 (all models) | 1462 | Estimate | 0.97 |
| Novel problem-solving ARC-AGI-2 | Sonnet 4.6 | 58.3 | Estimate | 0.97 |
| Novel problem-solving ARC-AGI-2 | Sonnet 4.5 | 13.6 | Estimate | 0.97 |
| Novel problem-solving ARC-AGI-2 | Opus 4.6 | 68.8 | Estimate | 0.97 |
| Novel problem-solving ARC-AGI-2 | Opus 4.5 | 37.6 | Estimate | 0.97 |
| Novel problem-solving ARC-AGI-2 | Gemini 3 Pro | 31.1 | Estimate | 0.97 |
| Novel problem-solving ARC-AGI-2 | GPT-5.2 (all models) | 54.2 | Estimate | 0.97 |
| Graduate-level reasoning GPQA Diamond | Sonnet 4.6 | 74.5 | Estimate | 0.30 |
| Graduate-level reasoning GPQA Diamond | Sonnet 4.5 | 63.4 | Estimate | 0.30 |
| Graduate-level reasoning GPQA Diamond | Opus 4.6 | 73.9 | Estimate | 0.30 |
| Graduate-level reasoning GPQA Diamond | Opus 4.5 | 70.6 | Estimate | 0.30 |
| Graduate-level reasoning GPQA Diamond | Gemini 3 Pro | 91.9 | Estimate | 0.97 |
| Graduate-level reasoning GPQA Diamond | GPT-5.2 (all models) | 93.2 | Estimate | 0.97 |
| Visual reasoning MMMU-Pro | Sonnet 4.6 | 75.05 | Estimate | 0.90 |
| Visual reasoning MMMU-Pro | Sonnet 4.5 | 68.9 | Estimate | 0.30 |
| Visual reasoning MMMU-Pro | Opus 4.6 | 77.3 | Estimate | 0.30 |
| Visual reasoning MMMU-Pro | Opus 4.5 | 73.9 | Estimate | 0.30 |
| Visual reasoning MMMU-Pro | GPT-5.2 (all models) | 79.95 | Estimate | 0.90 |
| Multilingual QA MMMLU | Sonnet 4.6 | 89.3 | Estimate | 0.50 |
| Multilingual QA MMMLU | Sonnet 4.5 | 89.5 | Estimate | 0.50 |
| Multilingual QA MMMLU | Opus 4.6 | 91.1 | Estimate | 0.50 |
| Multilingual QA MMMLU | Opus 4.5 | 90.8 | Estimate | 0.50 |
| Multilingual QA MMMLU | Gemini 3 Pro | 91.8 | Estimate | 0.50 |
| Multilingual QA MMMLU | GPT-5.2 (all models) | 89.6 | Estimate | 0.50 |
| Multilingual Q&A (MMMLU) | Sonnet 4.6 | 89.3 | Estimate | 0.50 |
| Multilingual Q&A (MMMLU) | Sonnet 4.5 | 89.5 | Estimate | 0.50 |
| Multilingual Q&A (MMMLU) | Opus 4.6 | 91.1 | Estimate | 0.50 |
| Multilingual Q&A (MMMLU) | Opus 4.5 | 90.8 | Estimate | 0.50 |
| Visual reasoning (MMMU-Pro) | Gemini 3 Pro | 81 | Estimate | 0.50 |
| Multilingual Q&A (MMMLU) | Gemini 3 Pro | 91.8 | Estimate | 0.50 |
| Multilingual Q&A (MMMLU) | GPT-5.2 (all models) | 89.6 | Estimate | 0.50 |
Max subscribers get the same data by API. API docs
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 b874b26cbdc4.
| Path | Returns | Plan | |
|---|---|---|---|
| GET | /api/v1/charts/b874b26cbdc4 | Title, publisher, date, form, point count; with a Max key, the data link | Open |
| GET | /api/v1/charts/b874b26cbdc4/data | Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV | Max |
| GET | /api/v1/charts/b874b26cbdc4/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/b874b26cbdc4/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.
Make one like this
This chart's shape, your numbers.
Live preview. Everything stays on your device.
Pick the form
Start from our replica of this chart, or from a simplified form. Either way your numbers start from this chart's real data.
Swap in your numbers
These are this chart's own names and numbers so you can see the shape. Type over any name or number; the preview redraws as you go. Replace every one with yours before you post.
These are this chart's numbers so you can see the shape. Replace every one with yours before you post.
Your brand
Export the picture
Free pictures carry a small "Made with ViralChart" line in the corner. That line is how other people find us.
More data from Anthropic
All chart dataQuestions people ask
How accurate are these numbers?
They are estimated from the image by two independent passes, with confidence 0.74 on a 0 to 1 scale. Printed numbers read well; values read off an axis can be a few percent off.
Can I reuse this data?
The numbers describe a chart that Anthropic published. The image, layout and styling belong to them. Use the numbers with a credit to the publisher, and make your picture from your own data.
How do I get the file?
The JSON, CSV and agent skill file are under the email gate on this page. In this prototype they are static files at /api/charts/b874b26cbdc4.json and /api/charts/b874b26cbdc4.skill.md.