#18xAI· released 2026-03-31

xAI: Grok 4.20.

Grok 4.20 is a reasoning model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...

View on OpenRouter ↗
Context
2.0M
Input $/1M
$1.25
Output $/1M
$2.50
Modality
text · image · file

Benchmarks

How these are aggregated →
Arena Elo
1551
LMArena — human blind votes
AA Index
63.0
Artificial Analysis composite
LiveBench
78.0
Contamination-resistant
GPQA
78.0%
Grad-level science reasoning
MMLU-Pro
79.0%
Broad knowledge
SWE-bench
68.0%
Real GitHub bugs (Verified)
Terminal-Bench
61.0%
Agentic shell tasks
ARC-AGI
40.0%
Abstract reasoning
Aider Polyglot
78.0%
Multi-language code editing
Speed
101 tok/s
Median output speed

Nearby on the leaderboard