# Claude Sonnet 4.6Thinking

> Source: Benchize (https://benchize.com) — https://benchize.com/models/claude-sonnet-4-6-thinking. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/claude-sonnet-4-6-thinking.

Anthropic

Canonical URL: https://benchize.com/models/claude-sonnet-4-6-thinking
Last updated: Wed, 21 Oct 2026 18:52:20 GMT

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

Anthropic

## Benchmarks

| Benchmark | Score | ± | Rank | Cost | Latency | Source |  |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [MedQA / indigenous](https://benchize.com/benchmarks/vals-ai%3Amedqa%3Aindigenous.md) | 91.9% | SE ±0.61 pp | 4 / 12 | $0.04 | 36.53source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 91.9 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.036776 \| USD \| per_test \| Lower is better \| \| `latency` \| 36.533 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Anthropic reasoning true Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.61 pp sourcePopulation 95 stderr 0.61 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) Source Vals AI Original model label anthropic/claude-sonnet-4-6 Source version 1 Observed 2026-10-21T16:46:00.691Z Evidence SHA-256 `d67905978d932f64698ebe9e230d9519e5bae1c9d7176dda8379dc3874b6f90f` Source locator `/tasks/indigenous/anthropic~1claude-sonnet-4-6` |  |  |  |  |  |  |  |
| [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 93.64% | — | 22 / 144 | — | — | [nc bench](https://www.nc-bench.com/models) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 93.64 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 83.09 \| percent \| category \| Higher is better \| \| `language` \| 97.58 \| percent \| category \| Higher is better \| \| `utility` \| 97.88 \| percent \| category \| Higher is better \| \| `reasoning` \| 89.61 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.3 \| percent \| category \| Higher is better \| \| `rule_following` \| 85.73 \| percent \| category \| Higher is better \| \| `hallucination` \| 96.98 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude Sonnet 4.6 (Reasoning) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Claude Sonnet 4.6 (Reasoning) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/28` |  |  |  |  |  |  |  |
| [MedQA / unbiased](https://benchize.com/benchmarks/vals-ai%3Amedqa%3Aunbiased.md) | 92.2% | SE ±0.6 pp | 5 / 12 | $0.03 | 31.05source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 92.2 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.031909 \| USD \| per_test \| Lower is better \| \| `latency` \| 31.054 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Anthropic reasoning true Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.6 pp sourcePopulation 95 stderr 0.6 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) Source Vals AI Original model label anthropic/claude-sonnet-4-6 Source version 1 Observed 2026-10-21T16:46:00.691Z Evidence SHA-256 `d67905978d932f64698ebe9e230d9519e5bae1c9d7176dda8379dc3874b6f90f` Source locator `/tasks/unbiased/anthropic~1claude-sonnet-4-6` |  |  |  |  |  |  |  |
| [MedQA / hispanic](https://benchize.com/benchmarks/vals-ai%3Amedqa%3Ahispanic.md) | 91.9% | SE ±0.61 pp | 4 / 12 | $0.04 | 35.09source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 91.9 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.035386 \| USD \| per_test \| Lower is better \| \| `latency` \| 35.094 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Anthropic reasoning true Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.61 pp sourcePopulation 95 stderr 0.61 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) Source Vals AI Original model label anthropic/claude-sonnet-4-6 Source version 1 Observed 2026-10-21T16:46:00.691Z Evidence SHA-256 `d67905978d932f64698ebe9e230d9519e5bae1c9d7176dda8379dc3874b6f90f` Source locator `/tasks/hispanic/anthropic~1claude-sonnet-4-6` |  |  |  |  |  |  |  |
| [MedQA / white](https://benchize.com/benchmarks/vals-ai%3Amedqa%3Awhite.md) | 92% | SE ±0.61 pp | 4 / 12 | $0.04 | 34.9source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 92 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.035394 \| USD \| per_test \| Lower is better \| \| `latency` \| 34.904 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Anthropic reasoning true Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.61 pp sourcePopulation 95 stderr 0.607 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) Source Vals AI Original model label anthropic/claude-sonnet-4-6 Source version 1 Observed 2026-10-21T16:46:00.691Z Evidence SHA-256 `d67905978d932f64698ebe9e230d9519e5bae1c9d7176dda8379dc3874b6f90f` Source locator `/tasks/white/anthropic~1claude-sonnet-4-6` |  |  |  |  |  |  |  |
| [SAGE / calculus](https://benchize.com/benchmarks/vals-ai%3Asage%3Acalculus.md) | 60.49% | SE ±6.32 pp | 23 / 36 | $0.46 | 207.52source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 60.494 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.458947 \| USD \| per_test \| Lower is better \| \| `latency` \| 207.52 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Anthropic reasoning true Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.32 pp sourcePopulation 91 stderr 6.324 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label anthropic/claude-sonnet-4-6 Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/calculus/anthropic~1claude-sonnet-4-6` |  |  |  |  |  |  |  |
| [MedQA / asian](https://benchize.com/benchmarks/vals-ai%3Amedqa%3Aasian.md) | 91.6% | SE ±0.62 pp | 4 / 12 | $0.04 | 36.66source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 91.6 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.036218 \| USD \| per_test \| Lower is better \| \| `latency` \| 36.664 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Anthropic reasoning true Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.62 pp sourcePopulation 95 stderr 0.62 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) Source Vals AI Original model label anthropic/claude-sonnet-4-6 Source version 1 Observed 2026-10-21T16:46:00.691Z Evidence SHA-256 `d67905978d932f64698ebe9e230d9519e5bae1c9d7176dda8379dc3874b6f90f` Source locator `/tasks/asian/anthropic~1claude-sonnet-4-6` |  |  |  |  |  |  |  |
| [MedQA / black](https://benchize.com/benchmarks/vals-ai%3Amedqa%3Ablack.md) | 92.75% | SE ±0.58 pp | 3 / 12 | $0.04 | 36.47source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 92.75 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.036805 \| USD \| per_test \| Lower is better \| \| `latency` \| 36.466 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Anthropic reasoning true Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.58 pp sourcePopulation 95 stderr 0.58 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) Source Vals AI Original model label anthropic/claude-sonnet-4-6 Source version 1 Observed 2026-10-21T16:46:00.691Z Evidence SHA-256 `d67905978d932f64698ebe9e230d9519e5bae1c9d7176dda8379dc3874b6f90f` Source locator `/tasks/black/anthropic~1claude-sonnet-4-6` |  |  |  |  |  |  |  |
| [MedQA / overall](https://benchize.com/benchmarks/vals-ai%3Amedqa%3Aoverall.md) | 92.06% | SE ±0.25 pp | 4 / 12 | $0.04 | 35.12source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 92.058 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.035415 \| USD \| per_test \| Lower is better \| \| `latency` \| 35.119 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Anthropic reasoning true Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.25 pp sourcePopulation 95 stderr 0.247 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) Source Vals AI Original model label anthropic/claude-sonnet-4-6 Source version 1 Observed 2026-10-21T16:46:00.691Z Evidence SHA-256 `d67905978d932f64698ebe9e230d9519e5bae1c9d7176dda8379dc3874b6f90f` Source locator `/tasks/overall/anthropic~1claude-sonnet-4-6` |  |  |  |  |  |  |  |

---
Cite as: Claude Sonnet 4.6Thinking — Benchize, https://benchize.com/models/claude-sonnet-4-6-thinking (retrieved 2026-10-21)