Skip to main content

Model profile

o3

OpenAIEstablishedReleased Apr 16, 2025
Data verified
Overall Score
47.89Public #131 of 200Verified #67 of 99
Arena Elo
1258
Eligible category ranks
0of 8
Price (1M tokens)
$2 in / $8 out
API pricing
Speed
118tok/s
Context
200K

Evidence coverage

16 of 321 tracked benchmarks are published. 2 are verified and 14 provisional. 7 of 8 categories are measured.

Updated July 20, 2026Methodology
Published / tracked
16 / 321
Verified
2
Provisional
14
Categories with evidence
7 / 8

Evidence by category

  • Agentic1 benchmark
    Reported
  • Coding1 benchmark
    Reported
  • Reasoning2 benchmarks
    Reported
  • Knowledge6 benchmarks
    Reported
  • Math3 benchmarks
    Mixed evidence
  • Multilingual0 benchmarks
    Not measured
  • Multimodal2 benchmarks
    Reported
  • Inst. Following1 benchmark
    Reported
ProprietaryReasoning
Confidence:
Low
base

o3 ranks #131 out of 200 models on the public leaderboard with an overall score of 47.89/100. It also ranks #67 out of 99 on the verified leaderboard. While not a frontier model, it offers specific advantages depending on the use case.

o3 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.

o3 sits inside the o3 family alongside o3-mini, o3-pro. 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.

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 47.6548.16

  1. Qwen3 Max
    Alibaba
    #12848.16
    Qwen3 Max is #128 with a score of 48.16.
    Compare
  2. o1
    OpenAI
    #12948.1
    o1 is #129 with a score of 48.1.
    Compare
  3. Gemini 2.5 Flash
    Google
    #13048.09
    Gemini 2.5 Flash is #130 with a score of 48.09.
    Compare
  4. o3Current model
    OpenAI
    #13147.89
    o3 is #131 with a score of 47.89.
  5. Claude 3.5 Sonnet
    Anthropic
    #13247.74
    Claude 3.5 Sonnet is #132 with a score of 47.74.
    Compare
  6. GLM-4.5-Air
    Z.AI
    #13347.7
    GLM-4.5-Air is #133 with a score of 47.7.
    Compare
  7. Qwen3.5 Flash
    Alibaba
    #13447.65
    Qwen3.5 Flash is #134 with a score of 47.65.
    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.

No eligible category percentile is available from the published evidence yet.

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 benchmarkReported70.1
CodingRank Not rankedWeight 20%1 benchmarkReported50.7
ReasoningRank Not rankedWeight 17%2 benchmarksReported57.2
KnowledgeRank Not rankedWeight 12%6 benchmarksReported54.6
MathRank Not rankedWeight 5%3 benchmarksMixed sources38.0
MultilingualWeight 7%0 benchmarksNot measuredNot measured
MultimodalRank Not rankedWeight 12%2 benchmarksReported72.0
Inst. FollowingRank Not rankedWeight 5%1 benchmarkReported85.0

Chatbot Arena performance

Scroll horizontally to inspect confidence intervals and vote counts.

Chatbot Arena Elo, confidence interval, and vote count by evaluation view
ViewEloConfidence intervalVotes
Text Overall1258Not availableNot available

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

80.7%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.
Coding1 benchmark
AA-SciCodeReported

Artificial Analysis SciCode

41.0%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

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.
CritPtReported

Critical Physics Tasks

1.1%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.
Knowledge6 benchmarks
Artificial Analysis Intelligence IndexReported
30.4%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

82.7%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

20.0%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

-15.3%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.
AA-Omniscience AccuracyReported

Artificial Analysis Omniscience Accuracy

38.4%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-Omniscience Hallucination RateReported

Artificial Analysis Omniscience Hallucination Rate

87.1%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.
Math3 benchmarks
FrontierMath v2 (Tiers 1-3)Benchmark exact

FrontierMath v2 Tiers 1-3

18.685%Weighted 30%
Source: Epoch AI FrontierMath v2 leaderboardProvenance: Epoch AI reports FrontierMath v2 Tiers 1-3 at 18.685% for o3-2025-04-16_high. BenchLM selects the highest published thinking effort for the model and stores the v2 benchmark slice separately.
FrontierMath v2 (Tier 4)Benchmark exact

FrontierMath v2 Tier 4

2.083%Weighted 10%
Source: Epoch AI FrontierMath v2 leaderboardProvenance: Epoch AI reports FrontierMath v2 Tier 4 at 2.083% for o3-2025-04-16_high. BenchLM selects the highest published thinking effort for the model and stores the v2 benchmark slice separately.
AA MATH-500Reported

Artificial Analysis MATH-500

99.2%Display only
Source: Artificial Analysis: math-500 leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Multimodal2 benchmarks
AA-MMMU-ProReported

Artificial Analysis MMMU-Pro

70.1%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.
Design Arena WebsiteReported

Design Arena Website Elo

1069Display only
Source: OpenRouter model benchmarksProvenance: Display-only Design Arena Website Elo synced from OpenRouter model benchmark metadata. It is excluded from BenchLM weighted scoring.
Inst. Following1 benchmark
AA-IFBenchReported

Artificial Analysis IFBench

71.4%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.

Frequently Asked Questions

How does o3 perform overall in AI benchmarks?

o3 has 16 published benchmark scores on BenchLM, but it does not yet have enough non-generated coverage to receive a global overall rank.

Is o3 good for knowledge and understanding?

o3 has visible benchmark coverage in knowledge and understanding, but BenchLM does not currently assign it a global category rank there.

Is o3 good for coding and programming?

o3 has visible benchmark coverage in coding and programming, but BenchLM does not currently assign it a global category rank there.

Is o3 good for mathematics?

o3 has visible benchmark coverage in mathematics, but BenchLM does not currently assign it a global category rank there.

Is o3 good for reasoning and logic?

o3 has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.

Is o3 good for agentic tool use and computer tasks?

o3 has visible benchmark coverage in agentic tool use and computer tasks, but BenchLM does not currently assign it a global category rank there.

Is o3 good for multimodal and grounded tasks?

o3 has visible benchmark coverage in multimodal and grounded tasks, but BenchLM does not currently assign it a global category rank there.

Is o3 good for instruction following?

o3 has visible benchmark coverage in instruction following, but BenchLM does not currently assign it a global category rank there.

Which sibling models are related to o3?

o3 belongs to the o3 family. Related variants on BenchLM include o3-mini, o3-pro.

Does o3 have full benchmark coverage on BenchLM?

Not yet. o3 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 o3?

o3 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.