Compare · ModelsLive · 2 picked · head to head
GPT-5.4 vs Claude Opus 4.5
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
GPT-5.4 wins on 11/13 benchmarks
GPT-5.4 wins 11 of 13 shared benchmarks. Leads in agentic · reasoning · knowledge.
Category leads
agentic·GPT-5.4reasoning·GPT-5.4arena·Claude Opus 4.5knowledge·GPT-5.4math·GPT-5.4coding·GPT-5.4
Hype vs Reality
Attention vs performance
GPT-5.4
#44 by perf·no signal
Claude Opus 4.5
#111 by perf·no signal
Best value
GPT-5.4
2.2x better value than Claude Opus 4.5
GPT-5.4
6.7 pts/$
$8.75/M
Claude Opus 4.5
3.0 pts/$
$15.00/M
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
Anthropic
$380.0B·Tier 1
Head to head
13 benchmarks · 2 models
GPT-5.4Claude Opus 4.5
APEX-Agents
GPT-5.4 leads by +17.5
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
GPT-5.4
35.9
Claude Opus 4.5
18.4
ARC-AGI
GPT-5.4 leads by +13.7
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
GPT-5.4
93.7
Claude Opus 4.5
80.0
ARC-AGI-2
GPT-5.4 leads by +36.3
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
74.0
Claude Opus 4.5
37.6
Chatbot Arena Elo · Overall
Claude Opus 4.5 leads by +2.0
GPT-5.4
1465.8
Claude Opus 4.5
1467.7
Chess Puzzles
GPT-5.4 leads by +32.0
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
GPT-5.4
44.0
Claude Opus 4.5
12.0
FrontierMath-2025-02-28-Private
GPT-5.4 leads by +26.9
FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning.
GPT-5.4
47.6
Claude Opus 4.5
20.7
FrontierMath-Tier-4-2025-07-01-Private
GPT-5.4 leads by +22.9
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
27.1
Claude Opus 4.5
4.2
GPQA diamond
GPT-5.4 leads by +9.7
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
91.1
Claude Opus 4.5
81.4
OTIS Mock AIME 2024-2025
GPT-5.4 leads by +9.2
OTIS Mock AIME 2024–2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
GPT-5.4
95.3
Claude Opus 4.5
86.1
PostTrainBench
GPT-5.4 leads by +2.9
GPT-5.4
20.2
Claude Opus 4.5
17.3
SimpleQA Verified
GPT-5.4 leads by +3.0
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
GPT-5.4
44.8
Claude Opus 4.5
41.8
SWE-Bench verified
GPT-5.4 leads by +0.2
GPT-5.4
76.9
Claude Opus 4.5
76.7
WeirdML
Claude Opus 4.5 leads by +6.3
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
GPT-5.4
57.4
Claude Opus 4.5
63.7
Full benchmark table
| Benchmark | GPT-5.4 | Claude Opus 4.5 |
|---|---|---|
APEX-Agents APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments. | 35.9 | 18.4 |
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 93.7 | 80.0 |
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. | 74.0 | 37.6 |
Chatbot Arena Elo · Overall | 1465.8 | 1467.7 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 44.0 | 12.0 |
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. | 47.6 | 20.7 |
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. | 27.1 | 4.2 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 91.1 | 81.4 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024–2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 95.3 | 86.1 |
PostTrainBench | 20.2 | 17.3 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 44.8 | 41.8 |
SWE-Bench verified | 76.9 | 76.7 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 57.4 | 63.7 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| GPT-5.4 | $2.50 | $15.00 | 1.1M tokens (~525 books) | $56.25 |
| Claude Opus 4.5 | $5.00 | $25.00 | 200K tokens (~100 books) | $100.00 |