# Claude Opus 4.6Thinking · 32768 tokens

> Source: Benchize (https://benchize.com) — https://benchize.com/models/claude-opus-4-6-thinking-budget-32768. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/claude-opus-4-6-thinking-budget-32768.

Anthropic

Canonical URL: https://benchize.com/models/claude-opus-4-6-thinking-budget-32768
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) | 40% | SE ±2.88 pp | 2 / 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` \| 0.4 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.4 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-2025-02-28-Private reasoningBudget 32K Reasoning effort Not reported sourceModelVersion claude-opus-4-6_32K ### Reported statistics Uncertainty Standard error: ±2.88 pp standardError 0.028817526385684453 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath.csv) Source epoch ai Original model label claude-opus-4-6 Source version FrontierMath-2025-02-28-Private Evaluated 2026-02-06T12:46:04.911Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `f5c92f0f0b9103abb02308fd428c0806e7c21b91e8a14d43edb8af77ce941598` Source locator `/rows/23` |  |  |  |  |  |
| [FrontierMath Tier 4 (2025-07-01 private)](https://benchize.com/benchmarks/epoch-ai%3Afrontiermath_tier_4.md) | 20.83% | SE ±5.92 pp | 2 / 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` \| 0.20833333333333334 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.20833333333333334 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-2025-07-01-Private reasoningBudget 32K Reasoning effort Not reported sourceModelVersion claude-opus-4-6_32K ### Reported statistics Uncertainty Standard error: ±5.92 pp standardError 0.05923816975988693 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4.csv) Source epoch ai Original model label claude-opus-4-6 Source version FrontierMath-Tier-4-2025-07-01-Private Evaluated 2026-02-06T12:46:05.800Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `c928e5adccd6e0995d50ede183fb99728d6c5be01951434a3077429ffb5802b2` Source locator `/rows/24` |  |  |  |  |  |
| [OTIS Mock AIME 2024–2025](https://benchize.com/benchmarks/epoch-ai%3Aotis_mock_aime_2024_2025.md) | 93.06% | SE ±3.34 pp | 39 / 124 | [epoch ai · OTIS Mock AIME 2024-2025](https://epoch.ai/data/benchmark_data.zip#file=otis_mock_aime_2024_2025.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.9305555555555556 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.9305555555555556 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion OTIS Mock AIME 2024-2025 reasoningBudget 32K Reasoning effort Not reported sourceModelVersion claude-opus-4-6_32K ### Reported statistics Uncertainty Standard error: ±3.34 pp standardError 0.03337013961212755 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=otis_mock_aime_2024_2025.csv) Source epoch ai Original model label claude-opus-4-6 Source version OTIS Mock AIME 2024-2025 Evaluated 2026-02-06T04:31:07.514Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `b7c9da8c0587c82f1e0d814ceb496c24308380b997a16203b6e5d39eb07f4f50` Source locator `/rows/187` |  |  |  |  |  |
| [GPQA Diamond](https://benchize.com/benchmarks/gpqa-diamond.md) | 90.53% | SE ±1.69 pp | 26 / 126 | [epoch ai · GPQA diamond](https://epoch.ai/data/benchmark_data.zip#file=gpqa_diamond.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.9053030303030303 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.9053030303030303 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion GPQA diamond reasoningBudget 32K Reasoning effort Not reported sourceModelVersion claude-opus-4-6_32K ### Reported statistics Uncertainty Standard error: ±1.69 pp standardError 0.016916245311450143 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=gpqa_diamond.csv) Source epoch ai Original model label claude-opus-4-6 Source version GPQA diamond Evaluated 2026-02-06T02:17:07.741Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `9ef0b938bdd8406b029d595983ee8ad3a80bd9d64b82605b91b5ce39ba650c39` Source locator `/rows/179` |  |  |  |  |  |

---
Cite as: Claude Opus 4.6Thinking · 32768 tokens — Benchize, https://benchize.com/models/claude-opus-4-6-thinking-budget-32768 (retrieved 2026-10-22)