# Grok 4.20Thinking

> Source: Benchize (https://benchize.com) — https://benchize.com/models/grok-4-20-thinking. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/grok-4-20-thinking.

xAI

Canonical URL: https://benchize.com/models/grok-4-20-thinking
Last updated: Thu, 22 Oct 2026 05:30:58 GMT

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

xAI

## Benchmarks

| Benchmark | Score | Rank | Cost | Source |  |
| --- | --- | --- | --- | --- | --- |
| [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 90.87% | 49 / 144 | — | [nc bench](https://www.nc-bench.com/models) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 90.87 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 86.25 \| percent \| category \| Higher is better \| \| `language` \| 96.61 \| percent \| category \| Higher is better \| \| `utility` \| 92.61 \| percent \| category \| Higher is better \| \| `reasoning` \| 74.28 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.83 \| percent \| category \| Higher is better \| \| `rule_following` \| 82.04 \| percent \| category \| Higher is better \| \| `hallucination` \| 96.3 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Grok 4.20 (Reasoning) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Grok 4.20 (Reasoning) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/60` |  |  |  |  |  |
| [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 65.14% | 68 / 243 | 0.92usd per task | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.6514 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.92 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup grok-4.20-beta-0309b-reasoning modelType CoT sourceModelVersion grok-4.20-beta-0309b-reasoning thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label Grok 4.20 (Reasoning) Source version v2 Observed 2026-10-22T05:20:04.306Z Evidence SHA-256 `4351eb696e78113b0459e9bb5f0258318b905efef34f473dcea51ce641b0d94d` Source locator `/evaluations/113` |  |  |  |  |  |
| [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 89.5% | 76 / 245 | 0.35usd per task | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.895 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.35 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup grok-4.20-beta-0309b-reasoning modelType CoT sourceModelVersion grok-4.20-beta-0309b-reasoning thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label Grok 4.20 (Reasoning) Source version v1 Observed 2026-10-22T05:20:04.066Z Evidence SHA-256 `2bf68d22dafba37047d07ad833ebc0e8199c9aa2f9eeaed50c75c1b704462836` Source locator `/evaluations/111` |  |  |  |  |  |

---
Cite as: Grok 4.20Thinking — Benchize, https://benchize.com/models/grok-4-20-thinking (retrieved 2026-10-22)