Compare · ModelsLive · 2 picked · head to head

GPT-4o (2024-05-13) vs o1-preview

Side by side · benchmarks, pricing, and signals you can act on.

Winner summary

o1-preview wins 5 of 5 shared benchmarks. Leads in coding · arena · knowledge.

Category leads
coding·o1-previewarena·o1-previewknowledge·o1-previewmath·o1-preview

Head to head · from the data · data as of 2026-11-22

  • Benchmarks · GPT-4o (2024-05-13) leads on 0 of 5 shared benchmarks, o1-preview on 5 (Aider · Code Editing, Chatbot Arena Elo · Overall, GPQA diamond, MATH level 5, 1 more)
  • Cheapest provider · GPT-4o (2024-05-13) at Azure $5.00/M input (1 offer) as of 2026-11-22
  • Price history · GPT-4o (2024-05-13) OpenRouter input list price had no move of 5% or more in the 90 days to 2026-11-22

Sources · scores from public leaderboards, list prices and provider offers from OpenRouter, price moves from the BenchGecko changelog (5% or more, held in the next daily check), Gecko tests run by BenchGecko.

Hype vs Reality
GPT-4o (2024-05-13)
#126 by perf·no signal
QUIET
o1-preview
#191 by perf·no signal
QUIET
Best value
GPT-4o (2024-05-13)
5.1 pts/$
$10.00/M
o1-preview
n/a
no price
Vendor risk
OpenAI logo
OpenAI
$840.0B·Tier 1
Medium risk
OpenAI logo
OpenAI
$840.0B·Tier 1
Medium risk
Head to head
GPT-4o (2024-05-13)o1-preview
Aider · Code Editing
o1-preview leads by +6.8
GPT-4o (2024-05-13)
72.9
o1-preview
79.7
Chatbot Arena Elo · Overall
o1-preview leads by +1309.3
GPT-4o (2024-05-13)
79.2
o1-preview
1388.5
GPQA diamond
o1-preview leads by +3.3
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
GPT-4o (2024-05-13)
31.9
o1-preview
35.2
MATH level 5
o1-preview leads by +30.6
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
GPT-4o (2024-05-13)
51.0
o1-preview
81.7
OTIS Mock AIME 2024-2025
o1-preview leads by +24.9
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
GPT-4o (2024-05-13)
6.2
o1-preview
31.0
Full benchmark table
BenchmarkGPT-4o (2024-05-13)o1-preview
Aider · Code Editing
72.979.7
Chatbot Arena Elo · Overall
79.21388.5
GPQA diamond
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
31.935.2
MATH level 5
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
51.081.7
OTIS Mock AIME 2024-2025
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
6.231.0
Pricing · per 1M tokens · projected $/mo at 10M tokens
ModelInputOutputContextProjected $/mo
OpenAI logoGPT-4o (2024-05-13)$5.00$15.00128K tokens (~64 books)$75.00
OpenAI logoo1-previewn/an/an/an/a
GPT-4o (2024-05-13) leads on 0 of 5 shared benchmarks, o1-preview on 5 (Aider · Code Editing, Chatbot Arena Elo · Overall, GPQA diamond, MATH level 5, 1 more)