Compare · ModelsLive · 2 picked · head to head
Claude Sonnet 4.5 vs GPT-5 Nano
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Claude Sonnet 4.5 wins on 11/12 benchmarks
Claude Sonnet 4.5 wins 11 of 12 shared benchmarks. Leads in reasoning · math · knowledge.
Category leads
reasoning·Claude Sonnet 4.5math·Claude Sonnet 4.5knowledge·Claude Sonnet 4.5coding·Claude Sonnet 4.5
Hype vs Reality
Attention vs performance
Claude Sonnet 4.5
#130 by perf·no signal
GPT-5 Nano
#112 by perf·no signal
Best value
GPT-5 Nano
43.0x better value than Claude Sonnet 4.5
Claude Sonnet 4.5
4.7 pts/$
$9.00/M
GPT-5 Nano
201.3 pts/$
$0.23/M
Vendor risk
Who is behind the model
Anthropic
$380.0B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
12 benchmarks · 2 models
Claude Sonnet 4.5GPT-5 Nano
ARC-AGI
Claude Sonnet 4.5 leads by +43.0
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
Claude Sonnet 4.5
63.7
GPT-5 Nano
20.7
ARC-AGI-2
Claude Sonnet 4.5 leads by +11.0
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
Claude Sonnet 4.5
13.6
GPT-5 Nano
2.6
FrontierMath-2025-02-28-Private
Claude Sonnet 4.5 leads by +6.9
FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning.
Claude Sonnet 4.5
15.2
GPT-5 Nano
8.3
FrontierMath-Tier-4-2025-07-01-Private
Claude Sonnet 4.5 leads by +2.1
FrontierMath Tier 4 (Jul 2025) · the most challenging tier of frontier mathematics, containing problems that push the absolute limits of AI mathematical reasoning.
Claude Sonnet 4.5
4.2
GPT-5 Nano
2.1
GPQA diamond
Claude Sonnet 4.5 leads by +17.2
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Claude Sonnet 4.5
76.4
GPT-5 Nano
59.3
MATH level 5
Claude Sonnet 4.5 leads by +2.5
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
Claude Sonnet 4.5
97.7
GPT-5 Nano
95.2
OTIS Mock AIME 2024-2025
GPT-5 Nano leads by +3.3
OTIS Mock AIME 2024–2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude Sonnet 4.5
77.8
GPT-5 Nano
81.1
SimpleQA Verified
Claude Sonnet 4.5 leads by +11.4
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Claude Sonnet 4.5
23.6
GPT-5 Nano
12.2
SWE-Bench Verified (Bash Only)
Claude Sonnet 4.5 leads by +35.8
SWE-Bench Verified (Bash Only) · a curated subset of SWE-bench where models fix real Python repository bugs using only bash commands, no agent frameworks.
Claude Sonnet 4.5
70.6
GPT-5 Nano
34.8
Terminal Bench
Claude Sonnet 4.5 leads by +35.0
Terminal Bench · tests the ability to accomplish real-world tasks using terminal commands, evaluating shell scripting and CLI tool proficiency.
Claude Sonnet 4.5
46.5
GPT-5 Nano
11.5
VPCT
Claude Sonnet 4.5 leads by +3.9
VPCT (Visual Pattern Completion Test) · tests visual reasoning and pattern recognition by having models complete visual sequences and transformations.
Claude Sonnet 4.5
9.7
GPT-5 Nano
5.8
WeirdML
Claude Sonnet 4.5 leads by +9.6
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Claude Sonnet 4.5
47.7
GPT-5 Nano
38.1
Full benchmark table
| Benchmark | Claude Sonnet 4.5 | GPT-5 Nano |
|---|---|---|
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 63.7 | 20.7 |
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. | 13.6 | 2.6 |
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. | 15.2 | 8.3 |
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. | 4.2 | 2.1 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 76.4 | 59.3 |
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics. | 97.7 | 95.2 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024–2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 77.8 | 81.1 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 23.6 | 12.2 |
SWE-Bench Verified (Bash Only) SWE-Bench Verified (Bash Only) · a curated subset of SWE-bench where models fix real Python repository bugs using only bash commands, no agent frameworks. | 70.6 | 34.8 |
Terminal Bench Terminal Bench · tests the ability to accomplish real-world tasks using terminal commands, evaluating shell scripting and CLI tool proficiency. | 46.5 | 11.5 |
VPCT VPCT (Visual Pattern Completion Test) · tests visual reasoning and pattern recognition by having models complete visual sequences and transformations. | 9.7 | 5.8 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 47.7 | 38.1 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| Claude Sonnet 4.5 | $3.00 | $15.00 | 1.0M tokens (~500 books) | $60.00 |
| GPT-5 Nano | $0.05 | $0.40 | 400K tokens (~200 books) | $1.38 |