xAIUnited States· released Sep 2025

Grok 4 Fast

Name: Grok 4 Fast
Author: xAI

Provisional: 7 comparable tests so far. Ranked once it reaches 6 across 3 counting categories.

xAI, United States. One of 8 models from this lab on the Index.

Third-party publishedLow confidence (thin coverage)

Snapshot September 8, 2026

OpenCharts Index

47.1

Provisional: not enough comparable tests or counting categories to rank yet · 7 comparable tests · 0 counting categories

Drop any single test and the Index lands between 40.1 and 51.4.

Needs more results (1 of 8 so far)

Averaging 5.6 on the 1 it has; the score opens at 4 of 8.

Distance to today's frontier on the hardest tests. Not a measure of intelligence.

What it's known for

Grok 4 Fast, in 7 results.

Its widest gap is on Code Arena (WebDev), 95.0% behind the best published result. No comparable results yet in knowledge, math and multimodal. Between 50% and 60% behind the best published results, on average.

Strongest category

No category counts yet: a category counts once it has more than one comparable test and the model has taken at least half of them. The scores it has are below.

Best single result

Fiction.LiveBench

Answer questions that need the whole of a very long story, at a 120K-token context length.

75.0%

75.0% of the best (100.0%) · #4 of 7.

Long documents are the normal case at work. This shows whether a model still holds the thread at the end.

Where it trails

Code Arena (WebDev)

Build a web app from the same prompt as a rival model; real users vote blind on the result.

1,162

95.0 points short of parity with the board leader (1,797) · #86 of 86.

People judging finished apps side by side is the most honest measure of front-end quality.

Not measured yet

No comparable result yet in these 3 categories. A blank is a blank, never a zero, and it does not lower the Index.

Knowledge
Math
Multimodal

Covered, but not averaged into the Index:

Reasoning2 of 6 tests · needs 3 · mean 27.4
Coding2 of 7 tests · needs 4 · mean 25.6
Agentic1 of 8 tests · needs 4 · mean 32.3
Human preferencesingle-test category, shown beside the Index · 75.0
Long contextsingle-test category, shown beside the Index · 75.0

Every score, with its source

See it at work

What Grok 4 Fast was asked to do, and how it did.

Every test it has taken, by category, with the kind of task it faced, who produced the number and where the result landed against the best published one. The examples are original and illustrative, never items from the datasets themselves.

Human preference · mean 75.0 across 1 comparable test · a single-test category, shown beside the Index and never averaged into it

Text ArenaLeaderboard

Answer the same prompt as a rival model; real users vote blind on which answer they prefer.

1,418

38% expected win rate against the board leader (1,507)
#73 of 92

board 2026-09-02

Source: Arena

Every result is read against the best published one on its test: percent scores as a share of the best above chance, Arena ratings as the expected win rate against the board leader, open-ended values on a log scale. Sitting a harder exam never lowers a model. Every number links to the publisher that produced it.

Head to head

Grok 4 Fast against whoever you pick.

Choose a rival. Every counted test both have taken appears side by side as a share of the best published result on that test, with the category means above. A win is a higher share; a gap under 2 points is a tie, because one item on a 45-problem exam is 2.2 points and publishers' own standard errors are of that order.

Grok 4 Fast

provisional·Index 47.1D

0 : 4

wins · 0 ties · 4 shared

GPT-6 Astra

#1·Index 99.0A+

GPT-6 Astra comes out ahead on 4 of the 4 tests both have taken.

Category means

Reasoning
27.4
99.6
Knowledge
—
100.0
Coding
25.6
97.7
Math
—
99.8
Agentic
32.3
98.5
Human preference
75.0
—
Long context
75.0
—

Shared tests · biggest gaps first

Code Arena (WebDev)Coding
1,162
1,797
−95.0
ARC-AGI-2Reasoning
5.3%
95.0%
−94.4
WeirdMLCoding
42.9%
92.9%
−53.9
ARC-AGI-1Reasoning
48.5%
98.5%
−50.8

Bars are distances to the best published result on each test (percent scores above chance, Arena ratings as win rate against the leader, open-ended values on a log scale). Raw values as the publishers report them.

Open GPT-6 Astra

Scores

Every test, every source

The best published run per benchmark, the raw value as the publisher reports it, who produced the number, how close it comes to the best published result on that test, and where the model sits among every model scored on it. Percent scores are read above chance, Arena ratings as a win rate against the board leader, open-ended values on a log scale. A test with too few models to compare against is shown but not counted.

Category means

Reasoning27.4 · 2/6
Knowledge—
Coding25.6 · 2/7
Math—
Agentic32.3 · 1/8
Multimodal—
Human preferencebeside75.0 · 1/1
Long contextbeside75.0 · 1/1

Mean · tests taken of the category's comparable tests. A faded category either rests on fewer than half of them or is a single-test category (marked “beside”), which is shown next to the Index and never averaged into it.

ARC-AGI-2LeaderboardReasoning

5.3%

5.6% of the best (95.0%)
14th percentile of 51 · n = 120

Source: Epoch AI — AI Benchmarking Hub

ARC-AGI-1LeaderboardReasoning

48.5%

49.2% of the best (98.5%)
8th percentile of 51 · n = 100

Source: Epoch AI — AI Benchmarking Hub

WeirdMLLeaderboardCoding

42.9%

46.1% of the best (92.9%)
15th percentile of 69

Source: Epoch AI — AI Benchmarking Hub