Skip to content
ModelCap

o3

Current board #52Arena #99API only7d #49 → #52

OpenAI·openai/o3

o3 is ModelCap current-board rank #52 with Index 63.9 (Measured), from the ModelCap Index as of 22 Sept 2026, 02:49 UTC.

o3 listed OpenRouter input price is $2.00 per 1M tokens and listed output price is $8.00 per 1M tokens, from OpenRouter listed prices as of 22 Sept 2026, 02:49 UTC.

o3 has a published context limit of 200K tokens in the ModelCap catalogue as of 22 Sept 2026, 02:49 UTC.

o3 has 1 published OpenRouter serving endpoint, from OpenRouter as of 22 Sept 2026, 02:49 UTC.

o3 weight access is api only, from ModelCap classification of published repository metadata as of 22 Sept 2026, 02:49 UTC.

Snapshot facts · download the public dataset · methodology

ModelCap Index · Current board
63.9#52
Measured · 65% support · score interval 59.1–68.7
Evidence as of 21 Sept 2026, 17:21 UTC
Market Gravity
19.5Decreased by 0.1
Secondary market signal
Input
$2.00
per 1M tokens
Output
$8.00
per 1M tokens
Context
200K
tokens
Providers
1
endpoint
Gateway spend
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
OpenAI$2.00$8.00200K100.0%

Other versions (1)

ModelCap Index · Current board

Methodology
63.9
Measured · 3 public benchmark observations across 3 boards
Current board
#52
Public rank basis
Measured (measured)
Index support
65.0% · strong
Index interval
59.1–68.7
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Evidence as of
21 Sept 2026, 17:21 UTC
Identity binding
Exact catalogue product · openai/openai/o3 · aggregates disclosed benchmark configurations · endpoint configuration not claimed
Index observations used
3
Qualified Index evidence point
63.9
Bayesian Evidence Score · measured evidence input only

BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.

Observed capability
63.9
Evidence status
confirmed · 87% mass
General preference
65.9
Coding
55.4
Agents & tools
Reasoning
30.8
Evidence breadth
95%
Evidence coverage
65%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
4.3
Liquidity (providers × uptime)
35.8
Open reach (HF downloads)
Surface (context / tools / modalities)
88.3
Freshness
13.6
  • · OpenRouter popularity #251
  • · 1 live provider
  • · Catalogue: context 200000, reasoning, tools, modalities Image/Text/File
  • · First seen 2025-04-16

These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.

BES evidence selected · measured input only

The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.

Deployment readiness

Metadata index
45.4
partial · 56% metadata coverage
Not capability
Artifact reproducibility
0.0
Access & legal clarity
30.3
Deployability
80.0
Evaluation provenance
76.9

Missing: artifactReproducibility.revision-sha, artifactReproducibility.architecture-and-model-type, artifactReproducibility.parameter-count, artifactReproducibility.serialized-weight-format, artifactReproducibility.base-lineage, accessLegalClarity.declared-license, accessLegalClarity.resolvable-license-terms, evaluationProvenance.evaluation-dataset-revisions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
19.5
OpenRouter weekly popularity
#251 of 322

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Arena preference

Status
Ranked
Source
LMArena
Official rank
#99 of 402
Rating
1431.6
95% confidence interval
1428–1435
Votes
59K
Source published at
13 Sept 2026, 00:00 UTC
Category
overall
Identity match confidence
99%

Market Gravity breakdown

Usage55%
4.3

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
35.8

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
50.0

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
13.6

Time since first public availability, on a six-month half-life.

Specification

Context window
200K tokens
Max output
100K tokens
Inputs
Image, Text, File
Outputs
Text
Tokenizer
GPT
Cached input tokens
$0.50 / 1M
First seen on OpenRouter
16 Apr 2025
Knowledge cutoff
2024-06-30

Capabilities

  • Supported: Reasoning
  • Supported: Tool use
  • Supported: Structured output
  • Supported: Response format
  • Supported: Moderated

Compare o3 with

Pick any model

Benchmark leaderboards featuring o3

All leaderboards
Public benchmark boards on which o3 has a published result
LeaderboardScoreSource rankConfigurationPublished
Arena coding leaderboardArena (LMArena)14601454–1467#125 of 397Default13 Sept 2026
ARC-AGI-2 leaderboardARC Prize Foundation6.5%#121 of 214High21 Sept 2026
SWE-bench leaderboardSWE-bench (Princeton / SWE-agent team)58.4%#27 of 47Default26 Jul 2025
BFCL V4 function-calling leaderboardUC Berkeley (Gorilla)63.1#7 of 83Prompt12 Apr 2026
τ²-Bench Telecom (Artificial Analysis run)Artificial Analysis80.7%#128 of 436tau2:telecom:dual-control:pass-at-1:3-repeats:source-model="o3":reasoning=true5 Sept 2026
Humanity's Last Exam (Artificial Analysis run)Artificial Analysis20.1%#177 of 615hle:may-2025:text-only-2158:no-tools:pass-at-1:source-model="o3":reasoning=true5 Sept 2026

Alternatives to o3, by the numbers

Ranked neighbours

Models within 3 places of #52 on the ModelCap Index.

Cheaper at a similar or higher Index

Index score within 3 points of, or above, this model's, with a lower listed blended price (3:1 input:output).

Other ranked OpenAI models

The same publisher's other current models with a public Index position.

o3: common questions

How does o3 rank among AI models?

o3 holds ModelCap Index position #52 of 248 ranked language models as of 22 September 2026, with an Index score of 63.9 (interval 59.1–68.7); evidence: measured. The Index combines public benchmark boards with published uncertainty; the methodology page explains the weighting.

How much does o3 cost per 1M tokens?

o3 is listed at $2.00 per 1M input tokens and $8.00 per 1M output tokens as of 22 September 2026. Prices come from the OpenRouter catalogue and re-observe on every refresh. For 1,000 requests using 2,000 input and 500 output tokens each, the listed rates imply $8.00 total (2M input + 0.5M output). This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the chosen endpoint's rate and limits before budgeting.

What is the context window of o3?

o3 has a published context window of 200K tokens (200,000) and a maximum output of 100K tokens. Individual providers can serve less than the published maximum; the providers table lists each endpoint's own limit.

Is o3 open-weight?

API only. No downloadable model weights are linked in the current source data; access is through a hosted API or product.

Which API providers serve o3?

One provider serves o3 through OpenRouter as of 22 September 2026: OpenAI. Each provider's price, context limit, quantization and measured uptime are in the providers table above.

Which benchmarks has o3 been evaluated on?

o3 has published results on 6 public boards tracked by ModelCap as of 22 September 2026: Arena coding 1460 (#125 of 397), ARC-AGI-2 6.5% (#121 of 214), SWE-bench 58.4% (#27 of 47), BFCL V4 63.1 (#7 of 83) and AA τ²-Bench Telecom 80.7% (#128 of 436) and more. Each board page ranks every tracked model on that benchmark; the ModelCap Index combines them with published uncertainty.

How does o3 compare with gemma 4 12B it?

o3 ranks #52 (Index 63.9) and gemma 4 12B it ranks #51 (Index 64.1) on the ModelCap Index as of 22 September 2026. The head-to-head page lines up their benchmarks, listed prices, context windows and provider counts side by side.

When was o3 released?

o3 first appeared in the catalogue on 16 Apr 2025, with a published knowledge cutoff of 2024-06-30. It is the current version in its family. Rank and price movements since then are recorded on the site's changes feed.