Skip to main content
BenchLM
Data

IFStruct

We show this table for reference; we do not rank on it.

Data verified

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

Benchmark score on IFStruct — October 29, 2026

We compile the IFStruct rows from provider self-reports. LFM3-1.7B is the only currently displayable sourced row, at 93.72%. We do not use these results to rank models overall.

1 modelInstruction FollowingCurrentDisplay onlyUpdated October 29, 2026

Benchmark score table (1 model)

Benchmark score results for IFStruct
RankModel / configurationScoreParameters (B)Open / closed
1LFM3-1.7BLiquidAI
93.72%
Not reportedOpen

How to read this leaderboard

Operator receipt: 1 sourced row is currently displayable on this page; the only currently displayable sourced row is LFM3-1.7B at 93.72%.

Honest limit: Only Liquid AI-run results are stored so far, from one launch table. Display-only and excluded from weighted ranking.

About IFStruct

Year

2026

Tasks

Structured-output instructions

Format

Accuracy

Difficulty

Exact format and schema compliance

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.

Freshness and provenance

Version

IFStruct 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Questions

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.

Last updated: October 29, 2026 · BenchLM version IFStruct 2026

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 6,100+ subscribers.

One email each week. Unsubscribe anytime.