Benchmark for instruction following capabilities.

IFBench

The Thinking checkpoint is a distinct reasoning tier that produces intermediate thinking traces before its final answer. It targets offline mathematics, instruction following, and tool selection on memory-constrained hardware. Quantized deployment can fit below 1GB, although exact memory and throughput depend on the hardware, precision, and context. Downloadable weights use the Liquid Open Model License, whose commercial-use conditions should be checked before deployment. Local inference supports private customization, while task reliability and performance require evaluation on the intended hardware.

LFM2.5 1.2B Thinking

This separately launched compact tier adds extended pretraining and reinforcement learning to Liquid’s 350M architecture. It focuses on structured output, extraction, and tool selection rather than lengthy general reasoning. Both base and post-trained weights are available for developers who need low-cost specialized inference on small edge devices. Downloadable weights use the Liquid Open Model License, whose commercial-use conditions should be checked before deployment. Local inference supports private customization, while task reliability and performance require evaluation on the intended hardware.

Rank	Model	Provider	Score	Parameters	Released	Type
1	LFM2.5 1.2B Thinking	Liquid AI	44.85	1.17B	2026-01-20	Text
2	LFM2.5 350M	Liquid AI	40.69	350M	2026-03-31	Text

IFBench

IFBench Leaderboard

About IFBench

Methodology

Publication

Related Benchmarks

Arena-Hard-v2

RACE