Grok 4.20 (Non-Reasoning)

Grok model for agentic tool use, reasoning, coding, and live assistance

BENCHMARKS

Not in the Epoch Capabilities Index. Epoch benchmarks what it can run, so this is a gap in coverage, not a poor result.

RELEASE DATEMar 9, 2026
WEIGHTSClosed weights
CONTEXT WINDOW1M
MAX OUTPUT30K
REASONINGNo
TOOL CALLINGYes
INPUTStext, image, pdf
OUTPUTStext

Specifications from Models.dev. Availability and limits may differ by provider. Benchmark scores come from Epoch AI under CC BY 4.0.