Compare · ModelsLive · 2 picked · head to head

GPT-4.5 vs GPT-4o (2024-11-20)

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

Winner summary

GPT-4.5 wins 10 of 11 shared benchmarks. Leads in coding · reasoning · knowledge.

Category leads
coding·GPT-4.5reasoning·GPT-4.5knowledge·GPT-4.5math·GPT-4.5
Hype vs Reality
GPT-4.5
#166 by perf·no signal
QUIET
GPT-4o (2024-11-20)
#156 by perf·no signal
QUIET
Best value
GPT-4.5
no price
GPT-4o (2024-11-20)
6.0 pts/$
$6.25/M
Vendor risk
OpenAI logo
OpenAI
$840.0B·Tier 1
Medium risk
OpenAI logo
OpenAI
$840.0B·Tier 1
Medium risk
Head to head
GPT-4.5GPT-4o (2024-11-20)
Aider polyglot
GPT-4.5 leads by +21.8
Aider Polyglot · measures how well AI models can edit code across multiple programming languages using the Aider coding assistant framework.
GPT-4.5
44.9
GPT-4o (2024-11-20)
23.1
ARC-AGI
GPT-4.5 leads by +5.8
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
GPT-4.5
10.3
GPT-4o (2024-11-20)
4.5
ARC-AGI-2
GPT-4.5 leads by +0.7
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
GPT-4.5
0.8
GPT-4o (2024-11-20)
0.1
Cybench
GPT-4.5 leads by +5.0
Cybench · evaluates AI on real Capture-The-Flag cybersecurity challenges, testing vulnerability analysis, exploitation, and security reasoning.
GPT-4.5
17.5
GPT-4o (2024-11-20)
12.5
GPQA diamond
GPT-4.5 leads by +26.0
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
GPT-4.5
58.3
GPT-4o (2024-11-20)
32.3
Lech Mazur Writing
GPT-4o (2024-11-20) leads by +6.2
Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication.
GPT-4.5
75.6
GPT-4o (2024-11-20)
81.8
MATH level 5
GPT-4.5 leads by +25.3
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
GPT-4.5
78.6
GPT-4o (2024-11-20)
53.3
OTIS Mock AIME 2024-2025
GPT-4.5 leads by +31.4
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
GPT-4.5
37.7
GPT-4o (2024-11-20)
6.3
SimpleBench
GPT-4.5 leads by +20.0
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
GPT-4.5
21.4
GPT-4o (2024-11-20)
1.4
VPCT
GPT-4.5 leads by +7.5
VPCT (Visual Pattern Completion Test) · tests visual reasoning and pattern recognition by having models complete visual sequences and transformations.
GPT-4.5
17.5
GPT-4o (2024-11-20)
10.0
WeirdML
GPT-4.5 leads by +14.2
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
GPT-4.5
39.4
GPT-4o (2024-11-20)
25.1
Full benchmark table
BenchmarkGPT-4.5GPT-4o (2024-11-20)
Aider polyglot
Aider Polyglot · measures how well AI models can edit code across multiple programming languages using the Aider coding assistant framework.
44.923.1
ARC-AGI
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
10.34.5
ARC-AGI-2
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
0.80.1
Cybench
Cybench · evaluates AI on real Capture-The-Flag cybersecurity challenges, testing vulnerability analysis, exploitation, and security reasoning.
17.512.5
GPQA diamond
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
58.332.3
Lech Mazur Writing
Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication.
75.681.8
MATH level 5
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
78.653.3
OTIS Mock AIME 2024-2025
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
37.76.3
SimpleBench
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
21.41.4
VPCT
VPCT (Visual Pattern Completion Test) · tests visual reasoning and pattern recognition by having models complete visual sequences and transformations.
17.510.0
WeirdML
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
39.425.1
Pricing · per 1M tokens · projected $/mo at 10M tokens
ModelInputOutputContextProjected $/mo
OpenAI logoGPT-4.5
OpenAI logoGPT-4o (2024-11-20)$2.50$10.00128K tokens (~64 books)$43.75