LIVE INTELLIGENCE · part of the Xentir AI Index

GPT-5.4 Mini vs Grok 4.3 Beta

Name: GPT-5.4 Mini vs Grok 4.3 Beta — benchmark results
Creator: Epoch AI
License: https://creativecommons.org/licenses/by/4.0/

GPT-5.4 Mini · OpenAI, released 2026-03-17
Grok 4.3 Beta · xAI, released 2026-04-17

“Epoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource].” · epoch.ai/benchmarks · Licensed CC BY 4.0 · data last verified 2026-09-09 · Methodology · Data Sources

Grok 4.3 Beta leads on more of the 5 benchmarks where both are measured — Grok 4.3 Beta on 5. The remaining 4 of 9 tracked benchmarks cannot be compared: 2 have a result for only one of the two models, 2 for neither. Nothing on this page is estimated to fill those in.

Head-to-head

Measured on 5 of 9 tracked benchmarks for both models — Grok 4.3 Beta leads on 5.

Benchmark	GPT-5.4 Mini	Grok 4.3 Beta	Leads
Epoch Capabilities Index (ECI)	149.0	149.2	Grok 4.3 Beta
SWE-bench Verified	Not measured	Not measured	Not measured on both
GPQA Diamond	0.869 (xhigh)	0.888 (high)	Grok 4.3 Beta
MATH Level 5	Not measured	Not measured	Not measured on both
OTIS Mock AIME 2024-2025	0.889 (xhigh)	0.933 (high)	Grok 4.3 Beta
FrontierMath	0.283 (high)	Not measured	Comparison unavailable — Grok 4.3 Beta has no published result
FrontierMath Tier 4	0.021 (high)	Not measured	Comparison unavailable — Grok 4.3 Beta has no published result
SimpleQA Verified	0.294 (high)	0.332 (high)	Grok 4.3 Beta
Chess Puzzles	0.240 (xhigh)	0.250 (high)	Grok 4.3 Beta

Benchmark results measure specific tasks and should not be treated as a universal measure of model quality. A model with no row here for a benchmark has not been measured on it — that is left blank, never estimated.

What remains uncertain

Grok 4.3 Beta has no published result on FrontierMath, FrontierMath Tier 4.
2 tracked benchmarks have no published result for either model.

A missing result means Xentir has not found one published by the source it cites, not that the model performs badly. See Data Sources.

Reference price

Per 1M tokens	GPT-5.4 Mini	Grok 4.3 Beta
Output	$4.50	—

List price as published by the vendor. Xentir does not verify negotiated or enterprise rates, and price is not a measure of capability — see Data Sources.

Full profiles

GPT-5.4 Mini → · Grok 4.3 Beta → · the full AI Model Rankings table