Compare · ModelsLive · 2 picked · head to head
GPT-5.4 Pro vs GPT-5.5
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
GPT-5.5 wins on 9/11 benchmarks
GPT-5.5 wins 9 of 11 shared benchmarks. Leads in reasoning · knowledge · math.
Category leads
reasoning·GPT-5.5knowledge·GPT-5.5math·GPT-5.5coding·GPT-5.5
Hype vs Reality
Attention vs performance
GPT-5.4 Pro
#40 by perf·#9 by attention
GPT-5.5
#64 by perf·#9 by attention
Best value
GPT-5.5
5.4x better value than GPT-5.4 Pro
GPT-5.4 Pro
0.6 pts/$
$105.00/M
GPT-5.5
3.3 pts/$
$17.50/M
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
11 benchmarks · 2 models
GPT-5.4 ProGPT-5.5
ARC-AGI
GPT-5.5 leads by +0.5
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
GPT-5.4 Pro
94.5
GPT-5.5
95.0
ARC-AGI-2
GPT-5.5 leads by +1.7
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
GPT-5.4 Pro
83.3
GPT-5.5
85.0
Chess Puzzles
GPT-5.5 leads by +2.5
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
GPT-5.4 Pro
58.6
GPT-5.5
61.1
FrontierMath-2025-02-28-Private
GPT-5.5 leads by +1.7
FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning.
GPT-5.4 Pro
50.0
GPT-5.5
51.7
FrontierMath-Tier-4-2025-07-01-Private
GPT-5.4 Pro leads by +2.1
FrontierMath Tier 4 (Jul 2025) · the most challenging tier of frontier mathematics, containing problems that push the absolute limits of AI mathematical reasoning.
GPT-5.4 Pro
37.5
GPT-5.5
35.4
FrontierMath-Tier-4-v2-Private
GPT-5.5 leads by +14.0
GPT-5.4 Pro
58.5
GPT-5.5
72.5
FrontierMath-Tiers-1-3-v2-Private
GPT-5.5 leads by +3.0
GPT-5.4 Pro
86.8
GPT-5.5
89.8
GPQA diamond
GPT-5.5 leads by +3.0
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
GPT-5.4 Pro
92.8
GPT-5.5
95.8
SimpleBench
GPT-5.4 Pro leads by +6.1
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
GPT-5.4 Pro
68.9
GPT-5.5
62.8
SimpleQA Verified
GPT-5.5 leads by +15.2
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
GPT-5.4 Pro
47.8
GPT-5.5
63.0
WeirdML
GPT-5.5 leads by +27.5
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
GPT-5.4 Pro
57.4
GPT-5.5
84.9
Full benchmark table
| Benchmark | GPT-5.4 Pro | GPT-5.5 |
|---|---|---|
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 94.5 | 95.0 |
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. | 83.3 | 85.0 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 58.6 | 61.1 |
FrontierMath-2025-02-28-Private FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning. | 50.0 | 51.7 |
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. | 37.5 | 35.4 |
FrontierMath-Tier-4-v2-Private | 58.5 | 72.5 |
FrontierMath-Tiers-1-3-v2-Private | 86.8 | 89.8 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 92.8 | 95.8 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 68.9 | 62.8 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 47.8 | 63.0 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 57.4 | 84.9 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $30.00 | $180.00 | 1.1M tokens (~525 books) | $675.00 | |
| $5.00 | $30.00 | 1.1M tokens (~525 books) | $112.50 |