Compare · ModelsLive · 2 picked · head to head
Claude Sonnet 4.6 vs GPT-5 Pro
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Claude Sonnet 4.6 wins on 3/4 benchmarks
Claude Sonnet 4.6 wins 3 of 4 shared benchmarks. Leads in reasoning · coding.
Category leads
reasoning·Claude Sonnet 4.6math·GPT-5 Procoding·Claude Sonnet 4.6
Hype vs Reality
Attention vs performance
Claude Sonnet 4.6
#104 by perf·#18 by attention
GPT-5 Pro
#124 by perf·no signal
Best value
Claude Sonnet 4.6
8.2x better value than GPT-5 Pro
Claude Sonnet 4.6
5.3 pts/$
$9.00/M
GPT-5 Pro
0.6 pts/$
$67.50/M
Vendor risk
Who is behind the model
Anthropic
$380.0B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
4 benchmarks · 2 models
Claude Sonnet 4.6GPT-5 Pro
ARC-AGI
Claude Sonnet 4.6 leads by +16.3
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
Claude Sonnet 4.6
86.5
GPT-5 Pro
70.2
ARC-AGI-2
Claude Sonnet 4.6 leads by +42.1
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 4.6
60.4
GPT-5 Pro
18.3
FrontierMath-Tier-4-2025-07-01-Private
GPT-5 Pro leads by +6.3
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 4.6
8.3
GPT-5 Pro
14.6
WeirdML
Claude Sonnet 4.6 leads by +5.7
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Claude Sonnet 4.6
66.1
GPT-5 Pro
60.4
Full benchmark table
| Benchmark | Claude Sonnet 4.6 | GPT-5 Pro |
|---|---|---|
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 86.5 | 70.2 |
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. | 60.4 | 18.3 |
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. | 8.3 | 14.6 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 66.1 | 60.4 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $3.00 | $15.00 | 1.0M tokens (~500 books) | $60.00 | |
| $15.00 | $120.00 | 400K tokens (~200 books) | $412.50 |