LIVE INTELLIGENCE · part of the Xentir AI Index

o3-mini

Name: o3-mini — benchmark results
Creator: Epoch AI
License: https://creativecommons.org/licenses/by/4.0/

OpenAI · Status: Active · Released 2025-01-31 · Accessibility: API access

“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

Xentir Snapshot

Best forScores in the top 9% of models measured on MATH Level 5 (0.965 (high)).

Watch out forNot yet measured on 1 of the 9 benchmarks Xentir tracks — see the breakdown below.

Benchmark breakdown

Benchmark	Score	Source
Epoch Capabilities Index (ECI) A composite index published by Epoch AI, aggregating results across multiple benchmark categories into a single capability score.	140.4	Epoch AI Benchmarking Hub
SWE-bench Verified Real-world GitHub issue resolution tasks, restricted to the human-verified subset of SWE-bench.	Not measured	Epoch AI Benchmarking Hub
GPQA Diamond Graduate-level multiple-choice questions in biology, physics and chemistry, written to resist search-engine lookup.	0.770 (high)	Epoch AI Benchmarking Hub
MATH Level 5 The hardest difficulty tier of competition mathematics problems in the MATH benchmark.	0.965 (high)	Epoch AI Benchmarking Hub
OTIS Mock AIME 2024-2025 Mock American Invitational Mathematics Examination problems from the OTIS problem sets.	0.769 (high)	Epoch AI Benchmarking Hub
FrontierMath Original, unpublished research-level mathematics problems.	0.124 (high)	Epoch AI Benchmarking Hub
FrontierMath Tier 4 The hardest difficulty tier within FrontierMath.	0.042 (high)	Epoch AI Benchmarking Hub
SimpleQA Verified Short factual questions, each with a single verifiable answer.	0.153 (high)	Epoch AI Benchmarking Hub
Chess Puzzles Tactical chess puzzles requiring one correct sequence of moves.	0.170 (high)	Epoch AI Benchmarking Hub

Benchmark results measure specific tasks and should not be treated as a universal measure of model quality.

Pricing

$1.10 per 1M input tokens · $4.40 per 1M output tokens · $0.55 per 1M cached input tokens

price as published by OpenAI, checked 2026-09-06. Vendor pricing page. List price only — Xentir does not verify negotiated or enterprise rates.

History

History begins 2026-07-26 — one data point so far. A trend needs at least two.

Compare

Latest Xentir coverage

OpenAI Reports GPT-5.6 Sol Runs Quantum Computing Experiments · 2026-09-08
OpenAI Expands Journalism Support From Classrooms to Newsrooms · 2026-09-08
OpenAI Introduces ChatGPT Images 2.5 · 2026-09-08

Sources and methodology

Scores on this page come from Epoch AI Benchmarking Hub, licensed CC BY 4.0. See the full methodology and data sources pages for how rankings, variants and ties are computed, and the full AI Model Rankings table for how o3-mini compares to every other measured model.