ModelsCompareBest forBenchmarksStatusPricingAPI

Grok 4.20 Reasoning

xAI·Pending·Released 2026-03-09textvision
Context1,000k
Max output-
Input / 1M$1.25 ↗
Output / 1M$2.5 ↗
Cached in$0.2
Benchmarks5

Benchmarks

Cited public sources · rank is exact-benchmark, apples-to-apples

FrontierMath Tier 4 v2 (Epoch AI run)#31/4417.1% ↗
FrontierMath Tiers 1-3 v2 (Epoch AI run)#37/5944.9% ↗
GPQA Diamond (Epoch AI run)#31/7789.3% ↗
OTIS Mock AIME 2024-2025 (Epoch AI run)#31/7692.2% ↗
SimpleQA Verified (Epoch AI run)#41/5330.2% ↗

Compare

vs GPT-6 Astravs GPT-5.6 Solvs GPT-5.6 Terravs GPT-5.6 Lunavs Claude Fable 5.1vs Claude Opus 5vs Claude Sonnet 5vs Claude Haiku 4.5

More from xAI

Grok 4.6Grok 4.3Grok 4.5Grok 4 Fast ReasoningGrok 4.20 Non-ReasoningGrok 4.20 Multi-Agent

Access Grok 4.20 Reasoning and every other model through one endpoint with automatic failover: Respan gateway.