Compare · ModelsLive · 3 picked · head to head
GPT-5.4 Pro vs GPT-5.2 Pro vs Claude Opus 4.8
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
GPT-5.4 Pro wins on 8/9 benchmarks
GPT-5.4 Pro wins 8 of 9 shared benchmarks. Leads in reasoning · math · knowledge.
Category leads
reasoning·GPT-5.4 Promath·GPT-5.4 Proknowledge·GPT-5.4 Procoding·Claude Opus 4.8
Hype vs Reality
Attention vs performance
GPT-5.4 Pro
#41 by perf·no signal
GPT-5.2 Pro
#77 by perf·no signal
Claude Opus 4.8
#47 by perf·no signal
Best value
Claude Opus 4.8
6.8x better value than GPT-5.4 Pro
GPT-5.4 Pro
0.6 pts/$
$105.00/M
GPT-5.2 Pro
0.6 pts/$
$94.50/M
Claude Opus 4.8
4.1 pts/$
$15.00/M
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
OpenAI
$840.0B·Tier 1
Anthropic
$380.0B·Tier 1
Head to head
9 benchmarks · 3 models
GPT-5.4 ProGPT-5.2 ProClaude Opus 4.8
ARC-AGI
GPT-5.4 Pro leads by +2.0
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-5.2 Pro
90.5
Claude Opus 4.8
92.5
ARC-AGI-2
GPT-5.4 Pro leads by +11.3
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-5.2 Pro
54.2
Claude Opus 4.8
72.1
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-5.4 Pro
37.5
GPT-5.2 Pro
31.3
Claude Opus 4.8
31.3
SimpleBench
GPT-5.4 Pro leads by +11.2
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-5.2 Pro
48.9
Claude Opus 4.8
57.8
Chess Puzzles
GPT-5.4 Pro leads by +24.6
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
Claude Opus 4.8
34.0
FrontierMath-2025-02-28-Private
GPT-5.4 Pro leads by +2.8
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
Claude Opus 4.8
47.2
GPQA diamond
GPT-5.4 Pro leads by +4.8
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
Claude Opus 4.8
88.0
SimpleQA Verified
GPT-5.4 Pro leads by +8.3
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
Claude Opus 4.8
39.5
WeirdML
Claude Opus 4.8 leads by +25.5
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
GPT-5.4 Pro
57.4
Claude Opus 4.8
82.9
Full benchmark table
| Benchmark | GPT-5.4 Pro | GPT-5.2 Pro | Claude Opus 4.8 |
|---|---|---|---|
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 94.5 | 90.5 | 92.5 |
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. | 83.3 | 54.2 | 72.1 |
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 | 31.3 | 31.3 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 68.9 | 48.9 | 57.8 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 58.6 | — | 34.0 |
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. | 50.0 | — | 47.2 |
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 | — | 88.0 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 47.8 | — | 39.5 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 57.4 | — | 82.9 |
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 | |
| $21.00 | $168.00 | 400K tokens (~200 books) | $577.50 | |
| $5.00 | $25.00 | 1.0M tokens (~500 books) | $100.00 |