all the models — AI benchmark observatory
← Benchmarks

AdvancedIF

AdvancedIF is a rubric-based benchmark measuring complex, multi-turn, and system-prompted instruction following ability, scored with a calibrated LLM judge against per-instruction rubrics.

id advancedif · max 1 · 2 models reported

#ModelScore

No scores for this benchmark yet.

AdvancedIF Leaderboard · all the models