Benchmark suiteLatest source data: Aug 27, 2026Checked: August 31, 2026

Grok 4.6 High.

A model-level benchmark profile for Grok 4.6 High, combining Arena category ranks, suite indexes, commercial price and speed data, SWE-bench status, and lab context.

xAI lab page

Lab

xAI

Proprietary

Coverage

56%

5 of 9 tracked signals

Best Arena rank

WebDev Arena

Best suite

#13

Coding / 72

Model profile

Benchmark signal map.

This view treats missing values as coverage gaps, then puts every available score, rank, cost, and speed signal into the same visual hierarchy.

Analyst view

Grok 4.6 High is strongest on coding.

56% coverage

Its best composite result is rank #13 in the coding view, with a 72 coding index. The strongest raw Arena signal is WebDev Arena at rank #5 with 1,523 public votes.

Best current lane

Coding

#13 / 72 coding index

Strongest raw signal

Code

#5, 1629 score

Commercial posture

$3.00

31.7s first token / 57 tok/s

Coverage gaps

Vision ArenaSearch ArenaDocument ArenaSWE-bench

Profile completeness

5 of 9 signals matched

56%

Arena categories

2/5

Code, Text

Commercial match

Live

Grok 4.6 (medium)

SWE-bench

Not listed

No confident software benchmark row

Raw identifier

grok-4.6-high

ReasoningCoding

Performance cockpit

Public benchmark scores

Arena rows show score, public rank, confidence interval, vote count, and publish date. Missing rows stay visible as coverage gaps.

Text Arena

Arena category

1,461#48

1451-1471 CI

3,471 votes

Aug 27, 2026

Arena public leaderboard dataset

WebDev Arena

Arena category

1,629#5

1612-1646 CI

1,523 votes

Aug 21, 2026

Arena public leaderboard dataset

Vision Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

Search Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

Document Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

SWE-bench Verified

Software issue resolution

Not listed

No confident SWE-bench row matched to this model.

Coverage gap

Cost and speed

Commercial profile

Price, latency, and throughput are only shown when a confident commercial source row is matched.

Blended price

$3.00

USD / 1M tokens

Input price

$2.00

USD / 1M input tokens

Output price

$6.00

USD / 1M output tokens

Latency

31.7s

Median time to first token

Output speed

57 tok/s

Median generation speed

Matched source row

Grok 4.6 (medium)

Suite position

Composite ranks by benchmark lens.

These views combine available public signals into purpose-specific indexes. A missing card means the model lacks enough source coverage for that lens.

Value

Quality, price, latency, and output speed

#3262

value index

blended / 1M tokens$3.00

time to first token31.7s

output speed57 tok/s

Coding

Code Arena, SWE-bench, and output speed

#1372

coding index

Code Arena rank #51,629