Compare · ModelsLive · 2 picked · head to head
GPT-5.2 Pro vs GPT-5.4 Pro
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
GPT-5.4 Pro wins on 6/6 benchmarks
GPT-5.4 Pro wins 6 of 6 shared benchmarks. Leads in reasoning · math.
Category leads
reasoning·GPT-5.4 Promath·GPT-5.4 Pro
Hype vs Reality
Attention vs performance
GPT-5.2 Pro
#61 by perf·#4 by attention
GPT-5.4 Pro
#37 by perf·#4 by attention
Best value
GPT-5.4 Pro
1.0x better value than GPT-5.2 Pro
GPT-5.2 Pro
0.6 pts/$
$94.50/M
GPT-5.4 Pro
0.6 pts/$
$105.00/M
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
6 benchmarks · 2 models
GPT-5.2 ProGPT-5.4 Pro
ARC-AGI
GPT-5.4 Pro leads by +4.0
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
GPT-5.2 Pro
90.5
GPT-5.4 Pro
94.5
ARC-AGI-2
GPT-5.4 Pro leads by +29.2
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
GPT-5.2 Pro
54.2
GPT-5.4 Pro
83.3
FrontierMath-Tier-4-2025-07-01-Private
GPT-5.4 Pro leads by +6.2
FrontierMath Tier 4 (Jul 2025) · the most challenging tier of frontier mathematics, containing problems that push the absolute limits of AI mathematical reasoning.
GPT-5.2 Pro
31.3
GPT-5.4 Pro
37.5
FrontierMath-Tier-4-v2-Private
GPT-5.4 Pro leads by +12.5
GPT-5.2 Pro
46.0
GPT-5.4 Pro
58.5
FrontierMath-Tiers-1-3-v2-Private
GPT-5.4 Pro leads by +8.5
GPT-5.2 Pro
74.0
GPT-5.4 Pro
82.5
SimpleBench
GPT-5.4 Pro leads by +20.0
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
GPT-5.2 Pro
48.9
GPT-5.4 Pro
68.9
Full benchmark table
| Benchmark | GPT-5.2 Pro | GPT-5.4 Pro |
|---|---|---|
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 90.5 | 94.5 |
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. | 54.2 | 83.3 |
FrontierMath-Tier-4-2025-07-01-Private FrontierMath Tier 4 (Jul 2025) · the most challenging tier of frontier mathematics, containing problems that push the absolute limits of AI mathematical reasoning. | 31.3 | 37.5 |
FrontierMath-Tier-4-v2-Private | 46.0 | 58.5 |
FrontierMath-Tiers-1-3-v2-Private | 74.0 | 82.5 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 48.9 | 68.9 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $21.00 | $168.00 | 400K tokens (~200 books) | $577.50 | |
| $30.00 | $180.00 | 1.1M tokens (~525 books) | $675.00 |