# Claude Sonnet 4.6Thinking · 16384 tokens

> Source: Benchize (https://benchize.com) — https://benchize.com/models/claude-sonnet-4-6-thinking-budget-16384. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/claude-sonnet-4-6-thinking-budget-16384.

Anthropic

Canonical URL: https://benchize.com/models/claude-sonnet-4-6-thinking-budget-16384
Last updated: Thu, 22 Oct 2026 04:40:22 GMT

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

Anthropic

## Benchmarks

| Benchmark | Score | ± | Rank | Source |  |
| --- | --- | --- | --- | --- | --- |
| [FrontierMath (2025-02-28 private)](https://benchize.com/benchmarks/epoch-ai%3Afrontiermath.md) | 32.4% | SE ±2.81 pp | 8 / 18 | [epoch ai · FrontierMath-2025-02-28-Private](https://epoch.ai/data/benchmark_data.zip#file=frontiermath.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.324 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.324 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-2025-02-28-Private reasoningBudget 16K Reasoning effort Not reported sourceModelVersion claude-sonnet-4-6_16K ### Reported statistics Uncertainty Standard error: ±2.81 pp standardError 0.028121636040639858 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath.csv) Source epoch ai Original model label claude-sonnet-4-6 Source version FrontierMath-2025-02-28-Private Evaluated 2026-02-20T14:53:58.744Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `f5c92f0f0b9103abb02308fd428c0806e7c21b91e8a14d43edb8af77ce941598` Source locator `/rows/18` |  |  |  |  |  |
| [FrontierMath Tier 4 (2025-07-01 private)](https://benchize.com/benchmarks/epoch-ai%3Afrontiermath_tier_4.md) | 8.3% | SE ±4 pp | 7 / 15 | [epoch ai · FrontierMath-Tier-4-2025-07-01-Private](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.083 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.083 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-2025-07-01-Private reasoningBudget 16K Reasoning effort Not reported sourceModelVersion claude-sonnet-4-6_16K ### Reported statistics Uncertainty Standard error: ±4 pp standardError 0.04 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4.csv) Source epoch ai Original model label claude-sonnet-4-6 Source version FrontierMath-Tier-4-2025-07-01-Private Evaluated 2026-02-21T20:36:46.695Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `c928e5adccd6e0995d50ede183fb99728d6c5be01951434a3077429ffb5802b2` Source locator `/rows/19` |  |  |  |  |  |
| [Short Story Writing — Pairwise Comparison](https://benchize.com/benchmarks/lechmazur-short-story%3Apairwise.md) | 1.66 | 95% CI 1.55–1.75 | 16 / 50 | [lechmazur short story · 8ba548d1cffefa5c472d3832e05f64e119a88fa4](https://api.github.com/repos/lechmazur/writing/contents/data/writing_gemini_argon_20261013/ratings.csv?ref=8ba548d1cffefa5c472d3832e05f64e119a88fa4) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `thurstone_rating` \| 1.6551236833288474 \| index \| pooled_observed_panel \| Higher is better \| \| `win_probability` \| 0.734654373626279 \| score_fraction \| comparison_pool \| Higher is better \| ### Configuration benchmarkScope data/writing_gemini_argon_20261013 reasoningBudget 16384 thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 1.55–1.75 bootstrapSamples 300 confidenceInterval95 ["1.5486216127951014","1.754013039176927"] sourceRank 16 ### Source [Original source](https://api.github.com/repos/lechmazur/writing/contents/data/writing_gemini_argon_20261013/ratings.csv?ref=8ba548d1cffefa5c472d3832e05f64e119a88fa4) Source lechmazur short story Original model label Claude Sonnet 4.6 Thinking 16K Source version 8ba548d1cffefa5c472d3832e05f64e119a88fa4 Observed 2026-10-21T16:34:21.130Z Evidence SHA-256 `c36baebed9f302ff7ad8fe97907d72e1757a015a39b6a3b23437597cf8e3bff6` Source locator `/rows/15` |  |  |  |  |  |

---
Cite as: Claude Sonnet 4.6Thinking · 16384 tokens — Benchize, https://benchize.com/models/claude-sonnet-4-6-thinking-budget-16384 (retrieved 2026-10-22)