# Grok 4.6Extra high

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

xAI

Canonical URL: https://benchize.com/models/grok-4-6-xhigh
Last updated: Thu, 22 Oct 2026 06:30:09 GMT

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

xAI

## Benchmarks

| Benchmark | Score | ± | Rank | Cost | Latency | Source |  |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [DeepSWE](https://benchize.com/benchmarks/deepswe%3Av1.1.md) | 66.74% | Range 64.56–68.92% | 24 / 70 | $5.5 | 1,272.35s | [deepswe](https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_at_1` \| 0.6674057649667405 \| score_fraction \| scored_rollout_attempts \| Higher is better \| \| `pass_at_4` \| 0.8495575221238938 \| score_fraction \| tasks_with_one_passing_rollout \| Higher is better \| \| `cost_per_attempt` \| 5.497668745011087 \| USD \| scored_attempt \| Lower is better \| \| `duration` \| 1272.3478393858093 \| seconds \| scored_attempt \| Lower is better \| ### Configuration harness mini-swe-agent Reasoning effort xhigh sourceConfiguration mini_swe_agent_grok_4_6_xhigh ### Reported statistics Uncertainty Reported interval: 64.56–68.92% interval [0.64564892272269,0.689162607210791] intervalMethod 95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R)) runCount 4 sampleSize 451 taskCount 113 ### Source [Original source](https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json) Source deepswe Original model label grok-4-6 Observed 2026-10-22T03:50:05.889Z Evidence SHA-256 `a7c15d66288fd249c020b9931c017b92d1a3b90e480b3ff34974b752bd030019` Source locator `/rows/23` |  |  |  |  |  |  |  |
| [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 67.08% | — | 63 / 243 | 0.76usd per task | — | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.6708333333333333 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.7574904499999999 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup xai-grok-4-6 modelType CoT Reasoning effort xhigh sourceModelVersion xai-grok-4-6-xhigh thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label Grok 4.6 (XHigh) Source version v2 Observed 2026-10-22T05:20:04.306Z Evidence SHA-256 `4351eb696e78113b0459e9bb5f0258318b905efef34f473dcea51ce641b0d94d` Source locator `/evaluations/209` |  |  |  |  |  |  |  |
| [ARC-AGI-3](https://benchize.com/benchmarks/arc-prize%3Av3_Semi_Private.md) | 2.11% | — | 23 / 65 | 5,612usd | — | [arc prize · v3](https://arcprize.org/media/data/leaderboard/v3.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.0211 \| score_fraction \| v3_Semi_Private \| Higher is better \| \| `total_cost` \| 5612 \| usd \| v3_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v3_Semi_Private harness standard modelGroup xai-grok-4-6 modelType CoT Reasoning effort xhigh sourceModelVersion xai-grok-4-6-xhigh thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v3.json) Source arc prize Original model label Grok 4.6 (XHigh) Source version v3 Observed 2026-10-22T05:20:04.578Z Evidence SHA-256 `3ce335487296bb2dcf4ba9546c5a2a02b1907db5b08887cd9ff4429fed824916` Source locator `/evaluations/26` |  |  |  |  |  |  |  |
| [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 87% | — | 92 / 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` \| 0.87 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.348182 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup xai-grok-4-6 modelType CoT Reasoning effort xhigh sourceModelVersion xai-grok-4-6-xhigh thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label Grok 4.6 (XHigh) Source version v1 Observed 2026-10-22T05:20:04.066Z Evidence SHA-256 `2bf68d22dafba37047d07ad833ebc0e8199c9aa2f9eeaed50c75c1b704462836` Source locator `/evaluations/208` |  |  |  |  |  |  |  |

---
Cite as: Grok 4.6Extra high — Benchize, https://benchize.com/models/grok-4-6-xhigh (retrieved 2026-10-22)