- Chart data
- Anthropic
- Claude 3.7 Sonnet benchmarks
Claude 3.7 Sonnet benchmarks
The numbers behind a chart Anthropic published, redrawn natively. Check the original, study the data, then make your own.
Simplified redraw
Drawn by us from the numbers below. Hover, tap or use the arrow keys.A simplified redraw: it shows the numbers in our own look, not the look of the original. One accent marks what the chart is about. Values marked with ~ in the table are estimates.
The numbers
First 10 of 56 points are free| Group | Series | Value | Source | Conf. |
|---|---|---|---|---|
| Graduate-level reasoning (GPQA Diamond) | Claude 3.7 Sonnet 64K extended thinking | ~78.2% | Estimate | 0.80 |
| Graduate-level reasoning (GPQA Diamond) | Claude 3.7 Sonnet No extended thinking | ~84.8% | Estimate | 0.80 |
| Graduate-level reasoning (GPQA Diamond) | Claude 3.5 Sonnet (new) | ~65% | Estimate | 0.80 |
| Graduate-level reasoning (GPQA Diamond) | OpenAI o3-mini High | 75.7% | Estimate | 0.30 |
| Graduate-level reasoning (GPQA Diamond) | OpenAI o3-mini | 78% | Estimate | 0.50 |
| Graduate-level reasoning (GPQA Diamond) | DeepSeek R1 32K extended thinking | 79.7% | Estimate | 0.30 |
| Graduate-level reasoning (GPQA Diamond) | Grok 3 Beta Extended thinking | 71.5% | Estimate | 0.30 |
| Graduate-level reasoning (GPQA Diamond) | Grok 3 Beta Extended thinking | 80.2% | Estimate | 0.50 |
| Graduate-level reasoning (GPQA Diamond) | Grok 3 Beta Extended thinking | 84.6% | Estimate | 0.50 |
| Agentic coding (SWE-bench Verified) | Claude 3.7 Sonnet 64K extended thinking | 62.3% | Estimate | 0.50 |
Max data, free with your email for now
See all 56 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) | Claude 3.7 Sonnet No extended thinking | 70.3% | Estimate | 0.30 |
|---|---|---|---|---|
| Agentic coding (SWE-bench Verified) | Claude 3.5 Sonnet (new) | 49% | Estimate | 0.50 |
| Agentic coding (SWE-bench Verified) | OpenAI o3-mini High | 48.9% | Estimate | 0.50 |
| Agentic coding (SWE-bench Verified) | OpenAI o3-mini | 49.3% | Estimate | 0.50 |
| Agentic coding (SWE-bench Verified) | DeepSeek R1 32K extended thinking | 49.2% | Estimate | 0.50 |
| Agentic tool use (TAU-bench) | Claude 3.7 Sonnet No extended thinking | ~81.2% | Estimate | 0.80 |
| Agentic tool use (TAU-bench) | Claude 3.5 Sonnet (new) | ~71.5% | Estimate | 0.80 |
| Agentic tool use (TAU-bench) | OpenAI o3-mini High | 73.5% | Estimate | 0.30 |
| Multilingual Q&A (MMMLU) | Claude 3.7 Sonnet 64K extended thinking | ~86.1% | Estimate | 0.80 |
| Multilingual Q&A (MMMLU) | Claude 3.7 Sonnet No extended thinking | ~83.2% | Estimate | 0.80 |
| Multilingual Q&A (MMMLU) | Claude 3.5 Sonnet (new) | ~82.1% | Estimate | 0.80 |
| Multilingual Q&A (MMMLU) | OpenAI o3-mini High | 87.7% | Estimate | 0.30 |
| Multilingual Q&A (MMMLU) | OpenAI o3-mini | 79.5% | Estimate | 0.50 |
| Visual reasoning (MMMU (validation)) | Claude 3.7 Sonnet 64K extended thinking | ~75% | Estimate | 0.80 |
| Visual reasoning (MMMU (validation)) | Claude 3.7 Sonnet No extended thinking | ~71.3% | Estimate | 0.80 |
| Visual reasoning (MMMU (validation)) | Claude 3.5 Sonnet (new) | ~70.4% | Estimate | 0.80 |
| Visual reasoning (MMMU (validation)) | OpenAI o3-mini High | 78.2% | Estimate | 0.50 |
| Instruction-following (IFEval) | Claude 3.7 Sonnet 64K extended thinking | ~93.2% | Estimate | 0.80 |
| Instruction-following (IFEval) | Claude 3.7 Sonnet No extended thinking | ~90.8% | Estimate | 0.80 |
| Instruction-following (IFEval) | Claude 3.5 Sonnet (new) | ~90.2% | Estimate | 0.80 |
| Instruction-following (IFEval) | DeepSeek R1 32K extended thinking | ~83.3% | Estimate | 0.80 |
| Instruction-following (IFEval) | Grok 3 Beta Extended thinking | 76% | Estimate | 0.50 |
| Instruction-following (IFEval) | Grok 3 Beta Extended thinking | 78% | Estimate | 0.50 |
| Math problem-solving (MATH 500) | Claude 3.7 Sonnet 64K extended thinking | ~96.2% | Estimate | 0.80 |
| Math problem-solving (MATH 500) | Claude 3.7 Sonnet No extended thinking | ~82.2% | Estimate | 0.80 |
| Math problem-solving (MATH 500) | Claude 3.5 Sonnet (new) | ~78% | Estimate | 0.80 |
| Math problem-solving (MATH 500) | OpenAI o3-mini High | ~97.15% | Estimate | 0.65 |
| Math problem-solving (MATH 500) | OpenAI o3-mini | 97.9% | Estimate | 0.50 |
| Math problem-solving (MATH 500) | DeepSeek R1 32K extended thinking | ~97.3% | Estimate | 0.80 |
| High school math competition (AIME 2024) | Claude 3.7 Sonnet 64K extended thinking | ~61.3% | Estimate | 0.80 |
| High school math competition (AIME 2024) | Claude 3.7 Sonnet No extended thinking | 80% | Estimate | 0.30 |
| High school math competition (AIME 2024) | Claude 3.5 Sonnet (new) | 23.3% | Estimate | 0.30 |
| High school math competition (AIME 2024) | OpenAI o3-mini High | 16% | Estimate | 0.30 |
| High school math competition (AIME 2024) | OpenAI o3-mini | 79.2% | Estimate | 0.50 |
| High school math competition (AIME 2024) | DeepSeek R1 32K extended thinking | 83.3% | Estimate | 0.30 |
| High school math competition (AIME 2024) | Grok 3 Beta Extended thinking | 87.3% | Estimate | 0.30 |
| High school math competition (AIME 2024) | Grok 3 Beta Extended thinking | 79.8% | Estimate | 0.50 |
| High school math competition (AIME 2024) | Grok 3 Beta Extended thinking | 83.9% | Estimate | 0.50 |
| High school math competition (AIME 2024) | Grok 3 Beta Extended thinking | 93.3% | Estimate | 0.50 |
| Graduate-level reasoning (GPQA Diamond) | OpenAI o1 | ~75.7% | Estimate | 0.30 |
| Agentic coding (SWE-bench Verified) | OpenAI o1 | ~78% | Estimate | 0.30 |
| Agentic tool use (TAU-bench) | OpenAI o1 | ~48.9% | Estimate | 0.30 |
| Multilingual Q&A (MMMLU) | OpenAI o1 | ~87.7% | Estimate | 0.30 |
| Visual reasoning (MMMU (validation)) | OpenAI o1 | ~78.2% | Estimate | 0.30 |
| Math problem-solving (MATH 500) | OpenAI o1 | ~96.4% | Estimate | 0.30 |
| High school math competition (AIME 2024) | OpenAI o1 | ~79.2% | Estimate | 0.30 |
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 75be1f405c8a.
| Path | Returns | Plan | |
|---|---|---|---|
| GET | /api/v1/charts/75be1f405c8a | Title, publisher, date, form, point count; with a Max key, the data link | Open |
| GET | /api/v1/charts/75be1f405c8a/data | Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV | Max |
| GET | /api/v1/charts/75be1f405c8a/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/75be1f405c8a/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
A simplified form: our own look, not the look of the original. Your numbers start from this chart's 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 0.55 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/75be1f405c8a.json and /api/charts/75be1f405c8a.skill.md.