Skip to main content

Model profile

o1

OpenAIEstablishedReleased December 2024
Data verified
Overall Score
48.1Public #129 of 200
Arena Elo
Not listed
Eligible category ranks
2of 8
Price (1M tokens)
$15 in / $60 out
API pricing
Speed
98tok/s
Context
200K

Evidence coverage

16 of 321 tracked benchmarks are published. 4 are verified and 12 provisional. 6 of 8 categories are measured.

Updated July 20, 2026Methodology
Published / tracked
16 / 321
Verified
4
Provisional
12
Categories with evidence
6 / 8

Evidence by category

  • Agentic1 benchmark
    Reported
  • Coding2 benchmarks
    Reported
  • Reasoning2 benchmarks
    Reported
  • Knowledge8 benchmarks
    Mixed evidence
  • Math1 benchmark
    Verified
  • Multilingual0 benchmarks
    Not measured
  • Multimodal0 benchmarks
    Not measured
  • Inst. Following2 benchmarks
    Mixed evidence
ProprietaryReasoning
Confidence:
Low
base

o1 ranks #129 out of 200 models on the public leaderboard with an overall score of 48.1/100. It does not yet have enough sourced coverage for BenchLM's verified leaderboard. While not a frontier model, it offers specific advantages depending on the use case.

o1 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 sits inside the o1 family alongside o1-preview, o1-pro. BenchLM links it directly to o1-preview as the earlier related model in that lineage. This profile currently has 16 of 321 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 Instruction Following (#18), while its weakest is Coding (#69). This performance profile makes it a well-rounded choice across a range of tasks.

Peer position

Exact provisional scores and ranks for the closest listed peers. A score can appear before a model clears the evidence threshold for a rank, so equal scores can have different rank states.

Range 47.748.33

  1. o3-pro
    OpenAI
    #12748.33
    o3-pro is #127 with a score of 48.33.
    Compare
  2. Qwen3 Max
    Alibaba
    #12848.16
    Qwen3 Max is #128 with a score of 48.16.
    Compare
  3. o1Current model
    OpenAI
    #12948.1
    o1 is #129 with a score of 48.1.
  4. Gemini 2.5 Flash
    Google
    #13048.09
    Gemini 2.5 Flash is #130 with a score of 48.09.
    Compare
  5. o3
    OpenAI
    #13147.89
    o3 is #131 with a score of 47.89.
    Compare
  6. Claude 3.5 Sonnet
    Anthropic
    #13247.74
    Claude 3.5 Sonnet is #132 with a score of 47.74.
    Compare
  7. GLM-4.5-Air
    Z.AI
    #13347.7
    GLM-4.5-Air is #133 with a score of 47.7.
    Compare

Category percentile

More

Relative position among models eligible for each sourced category. A higher percentile means a stronger position within that category's ranked cohort; 100 is highest.

  1. Inst. Following54%
    Eligible cohort rank #18 of 38Category score 85.4
  2. Coding44%
    Eligible cohort rank #69 of 122Category score 49.4

Category evidence

Scores and ranks appear only where this model has published benchmark evidence. Categories without displayable source records remain not measured.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank Not rankedWeight 22%1 benchmarkReported65.6
CodingRank #69 of 122Percentile 44thWeight 20%2 benchmarksReported49.4
ReasoningRank Not rankedWeight 17%2 benchmarksReported78.1
KnowledgeRank Not rankedWeight 12%8 benchmarksMixed sources64.4
MathRank Not rankedWeight 5%1 benchmarkVerified32.8
MultilingualWeight 7%0 benchmarksNot measuredNot measured
MultimodalWeight 12%0 benchmarksNot measuredNot measured
Inst. FollowingRank #18 of 38Percentile 54thWeight 5%2 benchmarksMixed sources85.4

Benchmark Details

Rows below have a displayable published verification record. Each source link and provenance note remains in the page HTML while its category is closed. Source-unverified manual rows and generated rows stay hidden.

Agentic1 benchmark
τ²-bench resultsReported

τ²-Bench Tool-Agent-User Evaluation

62.6%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Coding2 benchmarks
AA Coding IndexReported

Artificial Analysis Coding Index

39.7%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-SciCodeReported

Artificial Analysis SciCode

35.8%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Reasoning2 benchmarks
AA-LCRReported

Artificial Analysis Long Context Reasoning

59.3%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
CritPtReported

Critical Physics Tasks

0.3%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Knowledge8 benchmarks
GPQAProvider exact

Graduate-Level Google-Proof Q&A

75.7%Weighted 7%
Source: OpenAI: o1 and new tools for developersProvenance: Provider exact
MMLUProvider exact

Massive Multitask Language Understanding

91.8%Display only
Source: OpenAI: o1 and new tools for developersProvenance: Provider exact
Artificial Analysis Intelligence IndexReported
23.4%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-GPQA DiamondReported

Artificial Analysis GPQA Diamond

74.7%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-HLEReported

Artificial Analysis Humanity's Last Exam

7.7%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience IndexReported

Artificial Analysis Omniscience Index

-10.5%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience AccuracyReported

Artificial Analysis Omniscience Accuracy

34.7%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience Hallucination RateReported

Artificial Analysis Omniscience Hallucination Rate

69.3%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Math1 benchmark
FrontierMath v2 (Tiers 1-3)Benchmark exact

FrontierMath v2 Tiers 1-3

9.310%Weighted 30%
Source: Epoch AI FrontierMath v2 leaderboardProvenance: Epoch AI reports FrontierMath v2 Tiers 1-3 at 9.31% for o1-2024-12-17_high. BenchLM selects the highest published thinking effort for the model and stores the v2 benchmark slice separately.
Inst. Following2 benchmarks
IFEvalProvider exact

Instruction-Following Eval

92.2%Weighted 35%
Source: OpenAI: Introducing GPT-4.1 in the APIProvenance: Provider exact
AA-IFBenchReported

Artificial Analysis IFBench

70.3%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.

o1 Family

Base entry

Related Earlier Model

o1-preview

Frequently Asked Questions

How does o1 perform overall in AI benchmarks?

o1 has 16 published benchmark scores on BenchLM, but it does not yet have enough non-generated coverage to receive a global overall rank.

Is o1 good for knowledge and understanding?

o1 has visible benchmark coverage in knowledge and understanding, but BenchLM does not currently assign it a global category rank there.

Is o1 good for coding and programming?

o1 ranks #69 out of 122 models in coding and programming benchmarks with an average score of 49.4. There are stronger options in this category.

Is o1 good for mathematics?

o1 has visible benchmark coverage in mathematics, but BenchLM does not currently assign it a global category rank there.

Is o1 good for reasoning and logic?

o1 has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.

Is o1 good for agentic tool use and computer tasks?

o1 has visible benchmark coverage in agentic tool use and computer tasks, but BenchLM does not currently assign it a global category rank there.

Is o1 good for instruction following?

o1 ranks #18 out of 38 models in instruction following benchmarks with an average score of 85.4. There are stronger options in this category.

Which sibling models are related to o1?

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

Does o1 have full benchmark coverage on BenchLM?

Not yet. o1 currently has 16 published benchmark scores out of the 321 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?

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

Last updated: July 20, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Choose with this week’s evidence

Join 2,000+ readers for ranking moves, new releases, pricing changes, and the evidence behind them.

Free. One email per week.