Compare · ModelsLive · 2 picked · head to head
Claude 3.7 Sonnet vs GPT-5 Pro
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
GPT-5 Pro wins on 4/4 benchmarks
GPT-5 Pro wins 4 of 4 shared benchmarks. Leads in reasoning · knowledge.
Category leads
reasoning·GPT-5 Proknowledge·GPT-5 Pro
Hype vs Reality
Attention vs performance
Claude 3.7 Sonnet
#149 by perf·no signal
GPT-5 Pro
#183 by perf·#9 by attention
Vendor risk
Who is behind the model
Anthropic
$965.0B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
4 benchmarks · 2 models
Claude 3.7 SonnetGPT-5 Pro
ARC-AGI
GPT-5 Pro leads by +41.6
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
Claude 3.7 Sonnet
28.6
GPT-5 Pro
70.2
ARC-AGI-2
GPT-5 Pro leads by +17.4
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
Claude 3.7 Sonnet
0.9
GPT-5 Pro
18.3
HLE
GPT-5 Pro leads by +24.8
HLE (Humanity's Last Exam) · a reasoning benchmark designed to be the hardest public evaluation of AI. Questions span mathematics, physics, philosophy, and logic · curated to be at or beyond the frontier of human expert capability. Tested with and without tool augmentation.
Claude 3.7 Sonnet
3.4
GPT-5 Pro
28.2
SimpleBench
GPT-5 Pro leads by +18.2
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
Claude 3.7 Sonnet
35.7
GPT-5 Pro
53.9
Full benchmark table
| Benchmark | Claude 3.7 Sonnet | 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. | 28.6 | 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. | 0.9 | 18.3 |
HLE HLE (Humanity's Last Exam) · a reasoning benchmark designed to be the hardest public evaluation of AI. Questions span mathematics, physics, philosophy, and logic · curated to be at or beyond the frontier of human expert capability. Tested with and without tool augmentation. | 3.4 | 28.2 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 35.7 | 53.9 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| n/a | n/a | n/a | n/a | |
| $15.00 | $120.00 | 400K tokens (~200 books) | $412.50 |
People also compared