Inference
EN
OpenAI

o1-mini

o1-mini is a reasoning model from OpenAI. 12 benchmarks count toward its index, in 5 categories.

  • Closed weights
  • Reasoning
  • Input: text
  • Released 2024-09
RankedEnough results for an index.
IndexAll categories, out of 100.33.5±8.2Median 51.0
CoverageIndex weight that has results.65%
SpeedOutput tokens per second.—Median 67/s
First tokenSeconds to the first output token.—Median 1.3 s
Input / 1MUS dollars per 1M input tokens.$1.10Median $0.60
Output / 1MUS dollars per 1M output tokens.$4.40Median $2.55
ContextMaximum tokens in one request.128KMedian 262K
EloLMArena rating and rank.1317±4 #243Median 1422

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.None counted——
CodingCode writing and repair.1 counted32.7—
ReasoningLogic problems and puzzles.2 counted36.5182 / 227
MultimodalTasks with images and text.None counted——
KnowledgeFacts and expert knowledge.4 counted28.2244 / 268
MultilingualTasks in many languages.1 counted33.4—
InstructionTasks with strict prompt rules.None counted——
MathMath problems.4 counted37.2131 / 168

Results

12 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
Evaluating Large Language Models Trained on CodeCoding92.4%3 / 22
MATH level 5Math89.2% ±0.716 / 88
Multilingual Grade School MathMultilingual89.9%3 / 13
Massive Multitask Language UnderstandingKnowledge85.2%20 / 34
GPQA diamond · Epoch AIKnowledge62.4% ±2.7128 / 217
OTIS Mock AIME 2024-2025Math46.9% ±6.5125 / 200
Graduate-Level Google-Proof Q&AKnowledge60.0%110 / 141
Artificial Analysis GPQA DiamondKnowledge60.3%156 / 199
MATH-500 Problem SetMath90.0%22 / 27
FrontierMath-2025-02-28-PrivateMath1.4% ±0.758 / 69
ARC-AGI-2 (semi-private)Reasoning0.8%113 / 131
ARC-AGI-1 (semi-private)Reasoning14.0%113 / 126
Artificial Analysis Humanity's Last ExamKnowledge3.6%210 / 222
Measuring Short-Form Factuality in Large Language ModelsKnowledge7.6%14 / 14
MedQAHealthcare90.2% ±0.547 / 95
FrontierMath-2025-02-28-PublicMath0.0%33 / 64
ARC-AGI-2 (public eval)Reasoning0.0%102 / 122
ARC-AGI-1 (public eval)Reasoning13.2%106 / 116
Discrete Reasoning Over ParagraphsReasoning83.9%—

Sources

BenchLMCC BY-NC 4.0Epoch AICC BYARC Prize FoundationTerms restrict reuse

History

5 releases
Index34.6 → 33.5
23 Oct 202612 Nov 2026
Output / 1M$4.40 → $4.40
23 Oct 202612 Nov 2026

Questions

How much does o1-mini cost?
$1.10 per 1M input tokens, $4.40 per 1M output tokens.
How good is o1-mini?
Its index is 33.5 out of 100. That is place 241 of 283 ranked models.
What is o1-mini best at?
Math: 37.2 out of 100, place 131 of 168.
What is the context window of o1-mini?
128K tokens.
Is o1-mini open source?
No. Its weights are not published.
When was o1-mini released?
September 2024.

Badge

o1-mini on Inference360: place 241 of 283, index 33.5
HTML
<a href="https://inference360.ai/models/o1-mini"><img src="https://inference360.ai/badges/o1-mini.svg" alt="o1-mini on Inference360: place 241 of 283, index 33.5" height="20"></a>
Markdown
[![o1-mini on Inference360: place 241 of 283, index 33.5](https://inference360.ai/badges/o1-mini.svg)](https://inference360.ai/models/o1-mini)

Compare with

Celeris-133.7Magistral Medium33.7Granite 4.2 3B33.2GPT-4o mini26.2o144.5

Lower price

dots3-note Preview63.4 · FreeApodex 1.1 Mini55.7 · FreeNemotron 3 Ultra50.8 · Free

More from OpenAI

All models
o1-previewUnrankedGPT-4o AudioUnrankedGPT-4o mini26.2o144.5GPT-4o mini AudioUnranked