Compare · ModelsLive · 2 picked · head to head
Claude Sonnet 4.6 vs Grok 4 Fast
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Claude Sonnet 4.6 wins on 4/4 benchmarks
Claude Sonnet 4.6 wins 4 of 4 shared benchmarks. Leads in reasoning · general · coding.
Category leads
reasoning·Claude Sonnet 4.6general·Claude Sonnet 4.6coding·Claude Sonnet 4.6
Hype vs Reality
Attention vs performance
Claude Sonnet 4.6
#149 by perf·#10 by attention
Grok 4 Fast
#96 by perf·#15 by attention
Vendor risk
Who is behind the model
Anthropic
$965.0B·Tier 1
xAI
$250.0B·Tier 1
Head to head
4 benchmarks · 2 models
Claude Sonnet 4.6Grok 4 Fast
ARC-AGI
Claude Sonnet 4.6 leads by +38.0
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
Grok 4 Fast
48.5
ARC-AGI-2
Claude Sonnet 4.6 leads by +55.1
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
Grok 4 Fast
5.3
Dtbench
Claude Sonnet 4.6 leads by +12.0
Claude Sonnet 4.6
83.1
Grok 4 Fast
71.1
WeirdML
Claude Sonnet 4.6 leads by +23.2
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Claude Sonnet 4.6
66.1
Grok 4 Fast
42.9
Full benchmark table
| Benchmark | Claude Sonnet 4.6 | Grok 4 Fast |
|---|---|---|
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 86.5 | 48.5 |
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 | 5.3 |
Dtbench | 83.1 | 71.1 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 66.1 | 42.9 |
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 | |
| — | — | — | — |
People also compared