Compare · ModelsLive · 3 picked · head to head
Claude Opus 4.8 vs 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 9/11 benchmarks
GPT-5.4 Pro wins 9 of 11 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
Claude Opus 4.8
#75 by perf·#9 by attention
GPT-5.2 Pro
#61 by perf·#4 by attention
GPT-5.4 Pro
#37 by perf·#4 by attention
Best value
Claude Opus 4.8
6.0x better value than GPT-5.4 Pro
Claude Opus 4.8
3.7 pts/$
$15.00/M
GPT-5.2 Pro
0.6 pts/$
$94.50/M
GPT-5.4 Pro
0.6 pts/$
$105.00/M
Vendor risk
Who is behind the model
Anthropic
$965.0B·Tier 1
OpenAI
$840.0B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
11 benchmarks · 3 models
Claude Opus 4.8GPT-5.2 ProGPT-5.4 Pro
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.
Claude Opus 4.8
92.5
GPT-5.2 Pro
90.5
GPT-5.4 Pro
94.5
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.
Claude Opus 4.8
72.1
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.
Claude Opus 4.8
31.3
GPT-5.2 Pro
31.3
GPT-5.4 Pro
37.5
FrontierMath-Tier-4-v2-Private
GPT-5.4 Pro leads by +2.4
Claude Opus 4.8
56.1
GPT-5.2 Pro
46.0
GPT-5.4 Pro
58.5
FrontierMath-Tiers-1-3-v2-Private
GPT-5.4 Pro leads by +2.5
Claude Opus 4.8
80.0
GPT-5.2 Pro
74.0
GPT-5.4 Pro
82.5
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.
Claude Opus 4.8
57.8
GPT-5.2 Pro
48.9
GPT-5.4 Pro
68.9
Chess Puzzles
GPT-5.4 Pro leads by +25.9
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Claude Opus 4.8
30.6
GPT-5.4 Pro
56.4
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.
Claude Opus 4.8
47.2
GPT-5.4 Pro
50.0
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.
Claude Opus 4.8
88.0
GPT-5.4 Pro
92.8
SimpleQA Verified
Claude Opus 4.8 leads by +6.7
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Claude Opus 4.8
53.0
GPT-5.4 Pro
46.3
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.
Claude Opus 4.8
82.9
GPT-5.4 Pro
57.4
Full benchmark table
| Benchmark | Claude Opus 4.8 | 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. | 92.5 | 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. | 72.1 | 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 | 31.3 | 37.5 |
FrontierMath-Tier-4-v2-Private | 56.1 | 46.0 | 58.5 |
FrontierMath-Tiers-1-3-v2-Private | 80.0 | 74.0 | 82.5 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 57.8 | 48.9 | 68.9 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 30.6 | — | 56.4 |
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. | 47.2 | — | 50.0 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 88.0 | — | 92.8 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 53.0 | — | 46.3 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 82.9 | — | 57.4 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $5.00 | $25.00 | 1.0M tokens (~500 books) | $100.00 | |
| $21.00 | $168.00 | 400K tokens (~200 books) | $577.50 | |
| $30.00 | $180.00 | 1.1M tokens (~525 books) | $675.00 |