LFM2.5-2.6B vs LFM2.5-VL-3B: Specs & Benchmark Comparison

LFM2.5-2.6B and LFM2.5-VL-3B both come from Liquid AI, and both were released in August 2026. The two are similar in size, at about 3 billion and 3 billion parameters respectively.

The two models share 3 published benchmarks. LFM2.5-2.6B leads on 3 of them. The widest gaps are on IFBench, where LFM2.5-2.6B scores 59.2% against 25.8%; BFCL-V4, where LFM2.5-2.6B scores 56.9% against 32.5%. Averaged across everything we track, LFM2.5-2.6B sits at 55.5% and LFM2.5-VL-3B at 63.7%.

CharacteristicLFM2.5-2.6BLFM2.5-VL-3B
CompanyLiquid AILiquid AI
Release DateAugust 4, 2026August 12, 2026
Parameters3B3B
MultimodalNoYes
Average Score55.5%63.7%
Benchmarks
IFBench59.2%25.8%
BFCL-V456.9%32.5%
Multi-IF80.1%59.4%

Visual Benchmark Comparison

LFM2.5-2.6B
LFM2.5-VL-3B
IFBench0.6 vs 0.3
0.6
0.3
BFCL-V40.6 vs 0.3
0.6
0.3
Multi-IF0.8 vs 0.6
0.8
0.6

Verdict

Both models show equal results — the choice depends on your specific use case.

Overall Performance

Both models show comparable average scores: LFM2.5-2.6B — 0.6, LFM2.5-VL-3B — 0.6.

Recency

Both models were released around the same time: 8/4/2026 and 8/12/2026.

More About These Models

Related Comparisons

Frequently Asked Questions

Which is better for coding — LFM2.5-2.6B or LFM2.5-VL-3B?
Direct comparison on the SWE-Bench benchmark is not available. We recommend reviewing other metrics on the comparison page.
Which model is cheaper — LFM2.5-2.6B or LFM2.5-VL-3B?
API pricing data is available on the individual model pages.
Which has a larger context window — LFM2.5-2.6B or LFM2.5-VL-3B?
Context window data is available on the individual model pages.

The LFM2.5-2.6B and LFM2.5-VL-3B comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the LFM2.5-2.6B or LFM2.5-VL-3B page. See also the complete list of AI model comparisons.