Skip to main content

o1-preview

OpenAISupersededReleased Sep 12, 2024
Overall Score
Est. 83Prov. #18 of 119
Arena Elo
1388
Categories Ranked
8of 8
Price (1M tokens)
$15 in / $60 out
Speed
N/A
Context
200K
ProprietaryReasoning
Confidence
snapshot

According to BenchLM.ai, o1-preview ranks #18 out of 119 models on the provisional leaderboard with an overall score of 83/100. It does not yet have enough sourced coverage for BenchLM's verified leaderboard. This places it in the mid-tier of AI models, with strengths in specific benchmark categories.

o1-preview is a proprietary model with a 200K token context window. It uses explicit chain-of-thought reasoning, which typically improves performance on math and complex reasoning tasks at the cost of higher latency and token usage.

o1-preview sits inside the o1 family alongside o1, o1-pro. This profile currently has 2 of 225 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Agentic (#7), while its weakest is Instruction Following (#39). This performance profile makes it particularly useful for coding agents, browser research, and computer-use workflows.

Ranking Distribution

Category rank across 8 benchmark categories — sorted by best rank

Category Performance

Scores across all benchmark categories (0-100 scale)

Category Breakdown

Agentic

#7
90.1/ 100
Weight: 22%0 benchmarks
Terminal-Bench 2.0BrowseCompOSWorld-VerifiedGAIATAU-benchWebArena

Coding

#20
79.3/ 100
Weight: 20%1 benchmark
SWE-bench VerifiedLiveCodeBenchSWE-bench ProSWE-RebenchSciCode

Reasoning

#7
87.9/ 100
Weight: 17%0 benchmarks
MuSRLongBench v2MRCRv2ARC-AGI-2

Knowledge

#18
80.1/ 100
Weight: 12%1 benchmark
GPQASuperGPQAMMLU-ProHLEFrontierScienceSimpleQA

Math

#8
94.1/ 100
Weight: 5%0 benchmarks
AIME 2025BRUMO 2025MATH-500FrontierMath

Multilingual

#18
84.6/ 100
Weight: 7%0 benchmarks
MGSMMMLU-ProX

Multimodal

#33
66.9/ 100
Weight: 12%0 benchmarks
MMMU-ProOfficeQA ProCharXivCharXiv w/o tools

Inst. Following

#39
76.9/ 100
Weight: 5%0 benchmarks
IFEvalIFBench

Chatbot Arena Performance

Text Overall1388CI: ±5.031,122 votes
Coding1417CI: ±9.35,123 votes
Math1386CI: ±9.64,569 votes
Instruction Following1380CI: ±6.812,782 votes
Creative Writing1365CI: ±9.94,508 votes
Multi-turn1390CI: ±9.35,871 votes
Hard Prompts1396CI: ±7.78,496 votes
Hard Prompts (English)1413CI: ±9.44,917 votes
Longer Query1381CI: ±9.64,578 votes

Benchmark Details

Only benchmark rows with an attached exact-source record are shown here. Source-unverified manual rows and generated rows are hidden from model pages.

o1 Family

snapshot · preview

Canonical Entry

o1

Compare This Model

See how o1-preview stacks up against similar models

Frequently Asked Questions

How does o1-preview perform overall in AI benchmarks?

o1-preview currently ranks #18 out of 119 models on BenchLM's provisional leaderboard with an overall score of 83 (estimated). It is created by OpenAI and features a 200K context window.

Is o1-preview good for knowledge and understanding?

o1-preview ranks #18 out of 119 models in knowledge and understanding benchmarks with an average score of 80.1. There are stronger options in this category.

Is o1-preview good for coding and programming?

o1-preview ranks #20 out of 119 models in coding and programming benchmarks with an average score of 79.3. There are stronger options in this category.

Which sibling models are related to o1-preview?

o1-preview belongs to the o1 family. Related variants on BenchLM include o1, o1-pro.

Does o1-preview have full benchmark coverage on BenchLM?

Not yet. o1-preview currently has 2 published benchmark scores out of the 225 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of o1-preview?

o1-preview has a context window of 200K, which determines how much text it can process in a single interaction.

Last updated: June 2, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Don't miss the next GPT moment

Which models moved up, what’s new, and what it costs. One email a week, 3-min read.

Free. One email per week.