LIVE INTELLIGENCE · part of the Xentir AI Index

Grok-3 mini (Beta) vs o3-mini

Name: Grok-3 mini (Beta) vs o3-mini — benchmark results
Creator: Epoch AI
License: https://creativecommons.org/licenses/by/4.0/

Grok-3 mini (Beta) · xAI, released 2025-04-09
o3-mini · OpenAI, released 2025-01-31

“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

o3-mini leads on more of the 5 benchmarks where both are measured — Grok-3 mini (Beta) on 1, o3-mini on 3, tied on 1. The remaining 4 of 9 tracked benchmarks cannot be compared: 3 have a result for only one of the two models, 1 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-3 mini (Beta) leads on 1, o3-mini leads on 3, tied on 1.

Benchmark	Grok-3 mini (Beta)	o3-mini	Leads
Epoch Capabilities Index (ECI)	140.4	140.4	Tied
SWE-bench Verified	Not measured	Not measured	Not measured on both
GPQA Diamond	0.763 (low)	0.770 (high)	o3-mini
MATH Level 5	0.909 (low)	0.965 (high)	o3-mini
OTIS Mock AIME 2024-2025	0.778 (high)	0.769 (high)	Grok-3 mini (Beta)
FrontierMath	0.059 (high)	0.124 (high)	o3-mini
FrontierMath Tier 4	Not measured	0.042 (high)	Comparison unavailable — Grok-3 mini (Beta) has no published result
SimpleQA Verified	Not measured	0.153 (high)	Comparison unavailable — Grok-3 mini (Beta) has no published result
Chess Puzzles	Not measured	0.170 (high)	Comparison unavailable — Grok-3 mini (Beta) has no published result

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-3 mini (Beta) has no published result on Chess Puzzles, FrontierMath Tier 4, SimpleQA Verified.
1 tracked benchmark has 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	Grok-3 mini (Beta)	o3-mini
Output	—	$4.40

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

Grok-3 mini (Beta) → · o3-mini → · the full AI Model Rankings table