IFBench leaderboard
IFBench
1 models tested · Updated 2026-03-09 · Verified sources only
Grok 4.20 leads at 83.0%
1
Grok 4.20
xAI · Artificial Analysis · 2026-03-09
First place on instruction-following benchmark. From Artificial Analysis Intelligence Index v4.0.
83.0%
benchmark.space canonical public ledger of AI capability