Ctrl K
Back to models

OpenAI

o3

  • Released
  • Closed weights
Compare
Intelligence Index

Reasoning setting

20.2
Estimated · Artificial Analysis v4.3.2
API price from
$2.00 in / $8.00 out / 1M tokOpenRouter · OpenAI
Context window
200K tok

Performance profile

ReasoningRank #46 of 107
82.7%
GPQA Diamond

Capabilities

Context window

Modalities

Measured setting

Integration

Reasoning trade-offs

Source (opens in a new tab)
Intelligence Index v4.3.2
ReasoningEstimated
Intelligence Index
20.2

Pricing & access

API route
OpenRouter · OpenAIAPI
Tier & contextStandard

USD per 1M tokens

Input
$2.00
Output
$8.00
Cached input
$0.50

Benchmarks

Full leaderboardSource (opens in a new tab)

Humanity’s Last Exam

Frontier reasoning

o3 · Reasoning#64 of 126

  1. 1Claude Opus 5.5Max61.4%
  2. 2Claude Fable 5.1Max59.1%
  3. 3Gemini 4 ArgonHigh57.1%
  5. 61Muse GlimmerHigh22.0%
  6. 61Ling-3.0-flash-VLReasoning22.0%
  7. 63Ring-2.6-1TExtra high21.6%
  8. 64o3Reasoning20.1%
  9. 65GPT-5.5 Instant (June 2026)Reasoning19.9%
  10. 66gpt-oss-120bHigh19.6%
  11. 67Gemma 4 26B A4BReasoning19.3%

Peers use their best measured result on this benchmark.