Inference
EN
OpenAI

o1

o1 is a reasoning model from OpenAI. 20 benchmarks count toward its index, in 7 categories.

  • Closed weights
  • Reasoning
  • Input: text · image · file
  • Released 2024-12
RankedEnough results for an index.
IndexAll categories, out of 100.44.5±4.1Median 51.0
CoverageIndex weight that has results.95%
SpeedOutput tokens per second.97/sMedian 67/s
First tokenSeconds to the first output token.1.4 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$15.00Median $0.60
Output / 1MUS dollars per 1M output tokens.$60.00Median $2.55
ContextMaximum tokens in one request.200KMedian 262K
EloLMArena rating and rank.1366±4 #196Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
openai/o1
Max outputMaximum output tokens per request.
100K
Knowledge cutoffLast date of training data.
31 Oct 2023
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
Yes
Cache read / 1MUS dollars per 1M cached tokens.
$7.50
WeightsLink to the published weights.
—
RetiresDate OpenRouter removes the model.
—

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.1 counted44.3—
CodingCode writing and repair.1 counted31.0—
ReasoningLogic problems and puzzles.3 counted43.6147 / 227
MultimodalTasks with images and text.1 counted55.9—
KnowledgeFacts and expert knowledge.6 counted46.8159 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.2 counted51.836 / 63
MathMath problems.6 counted43.9110 / 168

Results

20 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
Massive Multitask Language UnderstandingKnowledge91.8%1 / 34
MATH level 5Math94.7% ±0.612 / 88
Instruction-Following EvalInstruction92.2%19 / 70
Artificial Analysis IFBenchInstruction70.3%43 / 146
MATH 500Math90.4% ±2.624 / 59
Artificial Analysis Omniscience AccuracyKnowledge34.5%70 / 164
GPQA diamond · Epoch AIKnowledge76.8% ±3.099 / 217
OTIS Mock AIME 2024-2025Math73.3% ±6.794 / 200
MMLU ProKnowledge83.5% ±0.471 / 135
Graduate-Level Google-Proof Q&AKnowledge75.7%77 / 141
SimpleQA VerifiedKnowledge41.1% ±1.650 / 91
FrontierMath-2025-02-28-PrivateMath9.3% ±1.738 / 69
AIMEMath71.5% ±1.553 / 95
τ²-Bench Tool-Agent-User EvaluationAgentic62.6%84 / 149
MMMU ProMultimodal77.4% ±1.053 / 92
Artificial Analysis GPQA DiamondKnowledge74.7%121 / 199
Artificial Analysis Long Context ReasoningReasoning65.0%135 / 217
GPQA Diamond · Vals AIKnowledge73.2% ±2.286 / 135
Critical Physics TasksReasoning0.3%137 / 214
Artificial Analysis Humanity's Last ExamKnowledge7.0%161 / 222
LiveCodeBenchCoding50.3% ±1.4116 / 142
Chess PuzzlesReasoning10.0% ±3.079 / 90
Artificial Analysis MATH-500Math97.0%8 / 9
FrontierMath-Tiers-1-3-v2-PrivateMath14.7% ±2.183 / 90
MedQAHealthcare96.5% ±0.31 / 95
TaxEval v2Finance74.3% ±0.938 / 143
FrontierMath-2025-02-28-PublicMath0.0%33 / 64
LegalBenchLegal80.4% ±0.686 / 149
MGSMMultilingual89.3% ±1.847 / 74

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reuseEpoch AICC BYVals AINo licence stated

History

5 releases
Index45.3 → 44.5
23 Oct 202612 Nov 2026
Output / 1M$60.00 → $60.00
23 Oct 202612 Nov 2026

Questions

How much does o1 cost?
$15.00 per 1M input tokens, $60.00 per 1M output tokens.
How good is o1?
Its index is 44.5 out of 100. That is place 181 of 283 ranked models.
What is o1 best at?
Instruction: 51.8 out of 100, place 36 of 63.
How fast is o1?
97 output tokens per second, 1.4 s to the first token.
What is the context window of o1?
200K tokens.
Is o1 open source?
No. Its weights are not published.
When was o1 released?
December 2024.

Badge

o1 on Inference360: place 181 of 283, index 44.5
HTML
<a href="https://inference360.ai/models/o1"><img src="https://inference360.ai/badges/o1.svg" alt="o1 on Inference360: place 181 of 283, index 44.5" height="20"></a>
Markdown
[![o1 on Inference360: place 181 of 283, index 44.5](https://inference360.ai/badges/o1.svg)](https://inference360.ai/models/o1)

Compare with

Gemma 4 26B A4B44.5o4-mini44.7Grok 3 Mini44.3o3-mini40.0o1-mini33.5

Lower price

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

More from OpenAI

All models
GPT-4o mini AudioUnrankedGPT-4o AudioUnrankedo3-mini40.0o3 Mini HighUnrankedo1-mini33.5