instruction following benchmark
AdvancedIF Leaderboard
AdvancedIF is a rubric-based benchmark for complex, multi-turn, and system-prompted instruction-following ability.
Updated Sep 5, 2026
Models2
Model coverage2
MetricScore
EvidenceB
AdvancedIF Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMI | Score85.00% | Percentile100.00% | Participants2 | EvidenceC | Evaluated |
| Rank02 | ModelMI | Score71.40% | Percentile0.00% | Participants2 | EvidenceC | Evaluated |
AdvancedIF Highlights
The leading models and scores on this benchmark.
AdvancedIF Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for AdvancedIF
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is AdvancedIF?
What AdvancedIF measures and how its scores work.
AdvancedIF is a rubric-based benchmark scored by a calibrated LLM judge against per-instruction rubrics.
It measures complex, multi-turn, and system-prompted instruction-following ability using the Score metric, reported as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- AdvancedIF
- Modality
- text
- Primary category
- instruction following
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about AdvancedIF.
Which model scores highest on AdvancedIF?
MAI-Thinking-1 is currently ranked first with 85.00%.
What are the top three models on AdvancedIF?
The current leaders are MAI-Thinking-1 (85.00%) and MAI-Code-1-Flash (71.40%).
Which AdvancedIF model has the lowest official input price?
No matched official input price is currently available.
Which models are fastest among AdvancedIF results?
No matched runtime record is currently available.
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.