IFHierBench: leaderboard

Metric: Prompt-level strict accuracy (%; share of prompts whose response satisfies every constraint in the tree; prompts whose output constraints are nested in a tree (artifact, sections, fields) of depth 0 to 3, checked by Python verifiers as in IFEval; 10 structure-level and 25 content-level constraint types). Source: arxiv.org. Saturation forecast: Around April 2027. 7 models tracked.

Top models

#ModelScore
1GPT-5.5 (High)53.7
2Claude Opus 4.6 (High)42.8
3Gemini 3 Flash (Preview)33.2
4DeepSeek R115.5
5Kimi K2.514.7

Interactive version: theaggregate.ai/benchmark?slug=ifhierbench · How It Works · Data refreshed daily, snapshot 2026-09-29.