xAIUnited States· released Jul 2026

Grok 4.5

Name: Grok 4.5
Author: xAI

Ranked #21, 35.8% behind the frontier on average.

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

Third-party publishedMedium confidence (7+ comparable tests, 3+ Index categories)

Snapshot September 8, 2026

OpenCharts Index

64.2

Ranked #21 (21 to 28) of 36 · 35.8% behind the frontier on average · 18 comparable tests · 3 counting categories

Drop any single test and the Index lands between 59.3 and 67.4, anywhere from #21 to #28. Neighbours inside that range are ties.

Needs more results (3 of 8 so far)

Averaging 47.1 on the 3 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 4.5, in 18 results.

Strongest in reasoning (74.8) and coding (64.1). It trails the frontier most in math, 46.3% behind on average. No comparable result yet in long context. Between 35% and 40% behind the best published results, on average. Drop any single test and it would sit anywhere from #21 to #28.

Strongest category

Reasoning

Hard, novel problems: graduate science, abstract puzzles, expert exams.

74.8

GPQA Diamond93.4% · 97% of best
ARC-AGI-187.2% · 89% of best
SimpleBench70.0% · 86% of best
ARC-AGI-252.6% · 55% of best
CritPt15.4% · 48% of best

Mean of 5 of the category's 6 comparable tests. Counts toward the Index.

Best single result

Mock AIME 2024–2025

Solve competition mathematics problems that have a single exact integer answer.

97.8%

97.8% of the best (100.0%) · #12 of 78.

Olympiad-style problems need long, careful chains of reasoning, and there is no partial credit.

Where it trails

FrontierMath Tier 4

Solve the hardest FrontierMath tier: problems that take expert mathematicians days.

24.4%

75.0% behind the best published result (97.6%) · #30 of 51.

The deepest end of the set. Progress here signals genuinely new capability.

Not measured yet

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

Long context

Covered, but not averaged into the Index:

Knowledgesingle-test category, shown beside the Index · 63.9
Agentic2 of 8 tests · needs 4 · mean 69.1
Multimodalsingle-test category, shown beside the Index · 91.1
Human preferencesingle-test category, shown beside the Index · 89.7

Every score, with its source

See it at work

What Grok 4.5 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.

Multimodal · mean 91.1 across 1 comparable test · a single-test category, shown beside the Index and never averaged into it

Vision ArenaLeaderboard

Answer prompts that include an image; real users vote blind between two models' answers.

1,282

46% expected win rate against the board leader (1,313)
#14 of 54

board 2026-08-27

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 4.5 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 4.5

#21·Index 64.2C

0 : 14

wins · 0 ties · 14 shared

GPT-6 Astra

#1·Index 99.0A+

GPT-6 Astra comes out ahead on 14 of the 14 tests both have taken.

Category means

Reasoning
74.8
99.6
Knowledge
63.9
100.0
Coding
64.1
97.7
Math
53.7
99.8
Agentic
69.1
98.5
Multimodal
91.1
—
Human preference
89.7
—

Shared tests · biggest gaps first

FrontierMath Tier 4Math
24.4%
97.6%
−75.0
ProofBenchMath
31.0%
99.0%
−68.0
Code Arena (WebDev)Coding
1,556
1,797
−60.1
CritPtReasoning
15.4%
31.7%
−50.4
WeirdMLCoding
46.4%
92.9%
−50.0
ARC-AGI-2Reasoning
52.6%
95.0%
−44.6
FrontierMath (Tiers 1–3)Math
57.2%
93.7%
−39.0
SimpleQA VerifiedKnowledge
48.3%
75.6%
−36.1
APEX-AgentsAgentic
34.2%
46.7%
−26.3
FrontierCodeCoding
42.4%
53.3%
−20.2
ARC-AGI-1Reasoning
87.2%
98.5%
−11.5
SciCodeCoding
54.1%
56.5%
−3.9
GPQA DiamondReasoning
93.4%
95.8%
−3.3
Mock AIME 2024–2025Math
97.8%
100.0%
−2.2

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

Reasoning74.8 · 5/6
Knowledgebeside63.9 · 1/1
Coding64.1 · 4/7
Math53.7 · 4/5
Agentic69.1 · 2/8
Multimodalbeside91.1 · 1/1
Human preferencebeside89.7 · 1/1
Long context—

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.

GPQA DiamondEpoch-runReasoning

93.4%

96.7% of the best (95.8%), above chance
90th percentile of 78 · n = 198

high

Grok 4.5

Grok 4.5, in 18 results.

What Grok 4.5 was asked to do, and how it did.

Grok 4.5 against whoever you pick.

Every test, every source

Compare with its neighbours.

The best models, ranked here, working inside Theo.