Grok 4 Thinking

Released2025-07-09
Price per 1MNot listed
Overall score54.0 (early, few results)
ProviderxAI
WeightsProprietary
ConfigurationThinking

Scores

DimensionScoreRankBenchmarks
Overall: Balanced 54.0 2
Overall: Coding 54.0 2
Overall: Reasoning 54.0 2
Overall: Agentic work 54.0 2
Reasoning 54.0 2

Evidence

Reasoning 54.0 ±2.1

BenchmarkResultSourceDate
ARC-AGI-2 (ARC Prize verified) 16.0% ARC Prize 2026-11-11
ARC-AGI-1 (ARC Prize verified) 66.7% ARC Prize 2026-11-11

Names matched to this model

grok-4-thinking

Compare Grok 4 Thinking with other models