# Claude 3.7 SonnetThinking

> Source: Benchize (https://benchize.com) — https://benchize.com/models/claude-3-7-sonnet-thinking. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/claude-3-7-sonnet-thinking.

Anthropic

Canonical URL: https://benchize.com/models/claude-3-7-sonnet-thinking
Last updated: Thu, 22 Oct 2026 07:32:33 GMT

Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations.

Anthropic

## Benchmarks

| Benchmark | Score | ± | Rank | Source |  |
| --- | --- | --- | --- | --- | --- |
| [Humanity’s Last Exam (HLE)](https://benchize.com/benchmarks/hle.md) | 8.04source score | CI 6.97–9.11 | 10 / 17 | [scale](https://labs.scale.com/leaderboard/humanitys_last_exam) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 8.04 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude 3.7 Sonnet (Thinking) sourceModelVersion Not reported thinkingEnabled true ### Reported statistics Uncertainty Confidence interval: 6.97–9.11 contaminationWarning Thinking budget: 16,000 tokens. Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. rank 38 reportedConfidenceHalfWidth 1.07 ### Source [Original source](https://labs.scale.com/leaderboard/humanitys_last_exam) Source scale Original model label Claude 3.7 Sonnet (Thinking) Observed 2026-10-22T03:30:08.991Z Evidence SHA-256 `2e7bc7983b3fe2fab5270a4dc00f51a40b87f5318a686fbae4291beda672f604` Source locator `/rows/37` |  |  |  |  |  |
| [Humanity's Last Exam (Preview)](https://benchize.com/benchmarks/scale%3Ahumanitys_last_exam_preview.md) | 8.93source score | CI 7.85–10.01 | 1 / 6 | [scale](https://labs.scale.com/leaderboard/humanitys_last_exam_preview) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 8.93 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude 3.7 Sonnet (thinking) sourceModelVersion Not reported thinkingEnabled true ### Reported statistics Uncertainty Confidence interval: 7.85–10.01 contaminationWarning Thinking budget: 16,000 tokens. Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. rank 3 reportedConfidenceHalfWidth 1.08 ### Source [Original source](https://labs.scale.com/leaderboard/humanitys_last_exam_preview) Source scale Original model label Claude 3.7 Sonnet (thinking) Observed 2026-10-22T03:30:14.541Z Evidence SHA-256 `e8cc24004a07ea6404481109c64fee06b0d5065657ad0230f31c704f7caa36ca` Source locator `/rows/2` |  |  |  |  |  |
| [Humanity's Last Exam (Text Only)](https://benchize.com/benchmarks/scale%3Ahumanitys_last_exam_text_only.md) | 7.89source score | CI 6.75–9.03 | 17 / 25 | [scale](https://labs.scale.com/leaderboard/humanitys_last_exam_text_only) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 7.89 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude 3.7 Sonnet (Thinking) sourceModelVersion Not reported thinkingEnabled true ### Reported statistics Uncertainty Confidence interval: 6.75–9.03 contaminationWarning Thinking budget: 16,000 tokens. Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. rank 44 reportedConfidenceHalfWidth 1.14 ### Source [Original source](https://labs.scale.com/leaderboard/humanitys_last_exam_text_only) Source scale Original model label Claude 3.7 Sonnet (Thinking) Observed 2026-10-22T03:30:09.372Z Evidence SHA-256 `16bd91dbd41a73afd31ff09fba3b9b08e9e3e2cfe682c50cc3b2bf8397610af6` Source locator `/rows/43` |  |  |  |  |  |
| [SVGBench Arena](https://benchize.com/benchmarks/svgbench%3Aarena.md) | 1,531 | — | 59 / 191 | [svgbench](https://svgbench.ai/api/leaderboard?shape=2) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1531 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_anthropic_claude_3_7_sonnet_thinking thinkingEnabled true ### Reported statistics coverageCount 27 draws 4 judged 77 losses 31 rank 73 ratingDeviation 28 wins 42 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Claude 3.7 Sonnet (thinking) Observed 2026-10-22T04:30:04.538Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/70` |  |  |  |  |  |
| [SimpleBench](https://benchize.com/benchmarks/simplebench%3Aavg-at-5.md) | 46.4% | — | 38 / 62 | [simplebench](https://simple-bench.com/static/js/leaderboard-data.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 46.4 \| percent \| average_at_5 \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude 3.7 Sonnet (thinking) thinkingEnabled true ### Reported statistics rank 60th ### Source [Original source](https://simple-bench.com/static/js/leaderboard-data.js) Source simplebench Original model label Claude 3.7 Sonnet (thinking) Observed 2026-10-22T03:40:04.693Z Evidence SHA-256 `b2d0285ad3e4e15750ed20d39897e7558d1c05e8962e90c861b06f93c8019dc9` Source locator `/rows/61` |  |  |  |  |  |

---
Cite as: Claude 3.7 SonnetThinking — Benchize, https://benchize.com/models/claude-3-7-sonnet-thinking (retrieved 2026-10-22)