Compare · ModelsLive · 3 picked · head to head
Claude Opus 4.6 (Fast) vs GPT-5 Pro vs o3 Pro
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
GPT-5 Pro wins on 3/5 benchmarks
GPT-5 Pro wins 3 of 5 shared benchmarks. Leads in reasoning · coding.
Category leads
knowledge·Claude Opus 4.6 (Fast)reasoning·GPT-5 Procoding·GPT-5 Pro
Hype vs Reality
Attention vs performance
Claude Opus 4.6 (Fast)
#122 by perf·no signal
GPT-5 Pro
#124 by perf·no signal
o3 Pro
#35 by perf·no signal
Best value
o3 Pro
1.9x better value than GPT-5 Pro
Claude Opus 4.6 (Fast)
0.5 pts/$
$90.00/M
GPT-5 Pro
0.6 pts/$
$67.50/M
o3 Pro
1.2 pts/$
$50.00/M
Vendor risk
Who is behind the model
Anthropic
$380.0B·Tier 1
OpenAI
$840.0B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
5 benchmarks · 3 models
Claude Opus 4.6 (Fast)GPT-5 Proo3 Pro
Professional Reasoning · Finance
Claude Opus 4.6 (Fast) leads by +2.2
Claude Opus 4.6 (Fast)
53.3
GPT-5 Pro
51.1
o3 Pro
49.1
Professional Reasoning · Legal
Claude Opus 4.6 (Fast) leads by +2.4
Claude Opus 4.6 (Fast)
52.3
GPT-5 Pro
49.9
o3 Pro
49.7
ARC-AGI
GPT-5 Pro leads by +10.9
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
GPT-5 Pro
70.2
o3 Pro
59.3
ARC-AGI-2
GPT-5 Pro leads by +13.5
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 Pro
18.3
o3 Pro
4.9
WeirdML
GPT-5 Pro leads by +2.2
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
GPT-5 Pro
60.4
o3 Pro
58.2
Full benchmark table
| Benchmark | Claude Opus 4.6 (Fast) | GPT-5 Pro | o3 Pro |
|---|---|---|---|
Professional Reasoning · Finance | 53.3 | 51.1 | 49.1 |
Professional Reasoning · Legal | 52.3 | 49.9 | 49.7 |
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | — | 70.2 | 59.3 |
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. | — | 18.3 | 4.9 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | — | 60.4 | 58.2 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $30.00 | $150.00 | 1.0M tokens (~500 books) | $600.00 | |
| $15.00 | $120.00 | 400K tokens (~200 books) | $412.50 | |
| $20.00 | $80.00 | 200K tokens (~100 books) | $350.00 |