Compare · ModelsLive · 2 picked · head to head
GPT-5 vs GPT-5.4
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
GPT-5.4 wins on 9/11 benchmarks
GPT-5.4 wins 9 of 11 shared benchmarks. Leads in agentic · reasoning · knowledge.
Category leads
agentic·GPT-5.4reasoning·GPT-5.4knowledge·GPT-5.4math·GPT-5.4coding·GPT-5.4
Hype vs Reality
Attention vs performance
GPT-5
#72 by perf·no signal
GPT-5.4
#44 by perf·no signal
Best value
GPT-5
1.4x better value than GPT-5.4
GPT-5
9.7 pts/$
$5.63/M
GPT-5.4
6.7 pts/$
$8.75/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-5GPT-5.4
APEX-Agents
GPT-5.4 leads by +17.6
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
GPT-5
18.3
GPT-5.4
35.9
ARC-AGI
GPT-5.4 leads by +28.0
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
GPT-5
65.7
GPT-5.4
93.7
ARC-AGI-2
GPT-5.4 leads by +64.1
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
9.9
GPT-5.4
74.0
Chess Puzzles
GPT-5.4 leads by +7.0
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
GPT-5
37.0
GPT-5.4
44.0
FrontierMath-2025-02-28-Private
GPT-5.4 leads by +15.2
FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning.
GPT-5
32.4
GPT-5.4
47.6
FrontierMath-Tier-4-2025-07-01-Private
GPT-5.4 leads by +14.6
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
12.5
GPT-5.4
27.1
GPQA diamond
GPT-5.4 leads by +9.5
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
GPT-5
81.6
GPT-5.4
91.1
OTIS Mock AIME 2024-2025
GPT-5.4 leads by +3.9
OTIS Mock AIME 2024–2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
GPT-5
91.4
GPT-5.4
95.3
SimpleQA Verified
GPT-5 leads by +5.8
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
GPT-5
50.6
GPT-5.4
44.8
SWE-Bench verified
GPT-5.4 leads by +3.3
GPT-5
73.5
GPT-5.4
76.9
WeirdML
GPT-5 leads by +3.3
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
GPT-5
60.7
GPT-5.4
57.4
Full benchmark table
| Benchmark | GPT-5 | GPT-5.4 |
|---|---|---|
APEX-Agents APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments. | 18.3 | 35.9 |
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 65.7 | 93.7 |
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. | 9.9 | 74.0 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 37.0 | 44.0 |
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. | 32.4 | 47.6 |
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. | 12.5 | 27.1 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 81.6 | 91.1 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024–2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 91.4 | 95.3 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 50.6 | 44.8 |
SWE-Bench verified | 73.5 | 76.9 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 60.7 | 57.4 |
Pricing · per 1M tokens · projected $/mo at 10M tokens