Compare · ModelsLive · 2 picked · head to head
Claude Opus 4.8 vs GPT-5.4
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Claude Opus 4.8 wins on 17/24 benchmarks
Claude Opus 4.8 wins 17 of 24 shared benchmarks. Leads in arena · knowledge · coding.
Category leads
agentic·GPT-5.4reasoning·GPT-5.4arena·Claude Opus 4.8knowledge·Claude Opus 4.8coding·Claude Opus 4.8general·Claude Opus 4.8math·Claude Opus 4.8
Hype vs Reality
Attention vs performance
Claude Opus 4.8
#75 by perf·#7 by attention
GPT-5.4
#104 by perf·#9 by attention
Best value
GPT-5.4
1.6x better value than Claude Opus 4.8
Claude Opus 4.8
3.7 pts/$
$15.00/M
GPT-5.4
6.0 pts/$
$8.75/M
Vendor risk
Who is behind the model
Anthropic
$965.0B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
24 benchmarks · 2 models
Claude Opus 4.8GPT-5.4
APEX-Agents
GPT-5.4 leads by +3.5
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
Claude Opus 4.8
48.9
GPT-5.4
52.4
ARC-AGI
GPT-5.4 leads by +1.2
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-5.4
93.7
ARC-AGI-2
GPT-5.4 leads by +1.9
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-5.4
74.0
Chatbot Arena Elo · Coding
Claude Opus 4.8 leads by +139.1
Claude Opus 4.8
1534.1
GPT-5.4
1395.0
Chatbot Arena Elo · Overall
Claude Opus 4.8 leads by +9.7
Claude Opus 4.8
1474.5
GPT-5.4
1464.8
Chess Puzzles
GPT-5.4 leads by +10.5
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
41.1
DeepResearch Bench
Claude Opus 4.8 leads by +15.1
DeepResearch Bench · evaluates AI on complex multi-step research tasks requiring information gathering, synthesis, and producing comprehensive analyses.
Claude Opus 4.8
50.2
GPT-5.4
35.1
Deepswe
Claude Opus 4.8 leads by +7.2
Claude Opus 4.8
59.0
GPT-5.4
51.8
Dtbench
Claude Opus 4.8 leads by +0.9
Claude Opus 4.8
91.5
GPT-5.4
90.7
Ebr Bench
Claude Opus 4.8 leads by +3.2
Claude Opus 4.8
28.6
GPT-5.4
25.4
FrontierMath-2025-02-28-Private
GPT-5.4 leads by +0.4
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
47.6
FrontierMath-Tier-4-2025-07-01-Private
Claude Opus 4.8 leads by +4.1
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-5.4
27.1
FrontierMath-Tier-4-v2-Private
Claude Opus 4.8 leads by +7.1
Claude Opus 4.8
56.1
GPT-5.4
49.0
FrontierMath-Tiers-1-3-v2-Private
Claude Opus 4.8 leads by +1.4
Claude Opus 4.8
80.0
GPT-5.4
78.6
Furniture Assembly
Claude Opus 4.8 leads by +7.1
Claude Opus 4.8
17.9
GPT-5.4
10.7
GPQA diamond
GPT-5.4 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.
Claude Opus 4.8
88.0
GPT-5.4
91.1
GSO-Bench
Claude Opus 4.8 leads by +15.7
GSO-Bench · evaluates AI models on real-world open-source software engineering tasks, testing the ability to understand and resolve actual GitHub issues.
Claude Opus 4.8
47.1
GPT-5.4
31.4
Lmca
Claude Opus 4.8 leads by +6.5
Claude Opus 4.8
67.7
GPT-5.4
61.1
Mystery Game Puzzles
GPT-5.4 leads by +1.1
Claude Opus 4.8
29.5
GPT-5.4
30.6
OTIS Mock AIME 2024-2025
Claude Opus 4.8 leads by +0.5
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude Opus 4.8
98.3
GPT-5.4
97.8
PostTrainBench
Claude Opus 4.8 leads by +14.8
Claude Opus 4.8
33.8
GPT-5.4
19.0
Proofbench
Claude Opus 4.8 leads by +13.0
Claude Opus 4.8
69.0
GPT-5.4
56.0
SimpleQA Verified
Claude Opus 4.8 leads by +7.9
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
45.1
WeirdML
Claude Opus 4.8 leads by +5.2
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
77.7
Full benchmark table
| Benchmark | Claude Opus 4.8 | 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. | 48.9 | 52.4 |
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 92.5 | 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. | 72.1 | 74.0 |
Chatbot Arena Elo · Coding | 1534.1 | 1395.0 |
Chatbot Arena Elo · Overall | 1474.5 | 1464.8 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 30.6 | 41.1 |
DeepResearch Bench DeepResearch Bench · evaluates AI on complex multi-step research tasks requiring information gathering, synthesis, and producing comprehensive analyses. | 50.2 | 35.1 |
Deepswe | 59.0 | 51.8 |
Dtbench | 91.5 | 90.7 |
Ebr Bench | 28.6 | 25.4 |
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 | 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. | 31.3 | 27.1 |
FrontierMath-Tier-4-v2-Private | 56.1 | 49.0 |
FrontierMath-Tiers-1-3-v2-Private | 80.0 | 78.6 |
Furniture Assembly | 17.9 | 10.7 |
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 | 91.1 |
GSO-Bench GSO-Bench · evaluates AI models on real-world open-source software engineering tasks, testing the ability to understand and resolve actual GitHub issues. | 47.1 | 31.4 |
Lmca | 67.7 | 61.1 |
Mystery Game Puzzles | 29.5 | 30.6 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 98.3 | 97.8 |
PostTrainBench | 33.8 | 19.0 |
Proofbench | 69.0 | 56.0 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 53.0 | 45.1 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 82.9 | 77.7 |
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 | |
| $2.50 | $15.00 | 1.1M tokens (~525 books) | $56.25 |