#17
Grok 4.5
xAI · Proprietary · Reasoning · 500K context
68/ 100 composite
Released 2026-07-08
Benchmark Scores by Category
Coding
55.0
Knowledge
69.5
Reasoning
61.2
Agentic
84.5
Multimodal
69.3
Scores based on weighted benchmarks: SWE-bench, LiveCodeBench (Coding); HLE, MMLU-Pro (Knowledge); ARC-AGI-2, LongBench v2 (Reasoning); Terminal-Bench, BrowseComp (Agentic); FrontierMath, AIME (Math).
API Pricing
Input
$2
per 1M tokens
Output
$6
per 1M tokens
Value Score
12.6
score per $1 output
Estimate Your Costs
Use our cost calculators to estimate monthly spend based on your specific workload: