ModelBeat
Models/Grok 4.3 Beta
All models
X
grok-4-3-beta

Grok 4.3 Beta is xAI’s proprietary AI model, released Apr 17, 2026. Its strongest use case is math, where it ranks in the 62nd percentile of the models Model Beat tracks.

Context
Input
/ 1M
Output
/ 1M
Released
Apr 17, 2026
Modalities
Strongest atMath top 38%

Benchmarks

Scores on standardized evaluations. Higher is better — and rank shows where Grok 4.3 Beta lands among all models tracked on Model Beat.

42.0
Intelligence Index
Epoch AI
42nd percentile of tracked models
22.0
Coding Index
Epoch AI
22nd percentile of tracked models

Reasoning

3 evals
GPQA Diamond88.8%

Graduate-level scientific reasoning

SimpleQA Verified33.2%

Factual accuracy & hallucination

WeirdML49.9%

Novel ML problem-solving

Coding

1 evals
WebDev Arena1357

Human-rated web development

Math

1 evals
AIME 2024/202593.3%

Olympiad-qualifier math

Changelog

1
  • Grok 4.3 Beta: reported SimpleQA Verified score fell from 38.0% to 33.2% (-13%)benchmark · Aug 28, 2026

Compare Grok 4.3 Beta with

Frequently asked questions

What is Grok 4.3 Beta?

Grok 4.3 Beta is a Grok-family AI model, from xAI, released Apr 17, 2026.

Who created Grok 4.3 Beta?

Grok 4.3 Beta is an AI model developed by xAI, part of the Grok family, released Apr 17, 2026.

How does Grok 4.3 Beta perform on benchmarks?

On standardized evaluations tracked by Epoch AI, Grok 4.3 Beta scores 88.8% on GPQA Diamond, 93.3% on AIME 2024/2025, 49.9% on WeirdML.

Is Grok 4.3 Beta open source?

Grok 4.3 Beta is a proprietary model (Hosted access (no API)), available through its provider's API rather than as a downloadable open-weight model.

Benchmark data from Epoch AI (CC BY) and Artificial Analysis; pricing, specs & descriptions from OpenRouter. Data updated Sep 4, 2026.