# IFStruct

> Liquid AI benchmark of following structured-output instructions, such as producing output that matches a requested schema or format.

Canonical page: https://benchlm.ai/benchmarks/ifstruct

- Category: [Instruction Following](/instruction-following)
- Last updated: October 29, 2026

## About IFStruct

- Year: 2026
- Tasks: Structured-output instructions
- Format: Accuracy
- Difficulty: Exact format and schema compliance
- Paper: [IFStruct v1.0](https://www.liquid.ai/blog/ifstruct-v1.0)

Liquid AI built IFStruct and reports it for LFM3-1.7B (October 27, 2026). Because the model's developer also owns the benchmark, read the result as a first-party measurement.

IFStruct is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (1 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [LFM3-1.7B](/models/lfm3-1-7b) | LiquidAI | 93.72% |

## FAQ

### What does IFStruct measure?

Liquid AI benchmark of following structured-output instructions, such as producing output that matches a requested schema or format.

### Which model scores highest on IFStruct?

LFM3-1.7B by LiquidAI currently leads with a score of 93.72% on IFStruct.

### How many models are evaluated on IFStruct?

1 AI models have published results on IFStruct in the BenchLM catalog.

### Does IFStruct affect BenchLM's overall score?

Not directly. IFStruct is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.