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

Inkling is developed by Thinking Machines Lab, while LFM2.5-VL-3B comes from Liquid AI. Inkling was released in July 2026, and LFM2.5-VL-3B followed a month later in August 2026. Inkling is the larger model at roughly 975 billion parameters, against 3 billion for LFM2.5-VL-3B.

The two models share 2 published benchmarks. Inkling leads on 2 of them. The widest gaps are on IFBench, where Inkling scores 79.8% against 25.8%; MMMU-Pro, where Inkling scores 73.5% against 30.5%. Averaged across everything we track, Inkling sits at 61.8% and LFM2.5-VL-3B at 63.7%.

Inkling is available through an API at $0.95 per million input tokens with a 524K-token context window. We do not track a hosted API for LFM2.5-VL-3B, so pricing and context cannot be compared directly.

CharacteristicInklingLFM2.5-VL-3B
CompanyThinking Machines LabLiquid AI
Release DateJuly 21, 2026August 12, 2026
Parameters975B3B
MultimodalYesYes
Context (input)524K
Context (output)524K
Input Price / 1M$0.95
Output Price / 1M$4.05
Average Score61.8%63.7%
Benchmarks
IFBench79.8%25.8%
MMMU-Pro73.5%30.5%

Visual Benchmark Comparison

Inkling
LFM2.5-VL-3B
IFBench0.8 vs 0.3
0.8
0.3
MMMU-Pro0.7 vs 0.3
0.7
0.3

Verdict

LFM2.5-VL-3B leads in 1 out of 2 comparison categories.

Overall Performance

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

Recency

LFM2.5-VL-3B is newer: released 8/12/2026 vs 7/21/2026.

More About These Models

Related Comparisons

Frequently Asked Questions

Which is better for coding — Inkling 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 — Inkling or LFM2.5-VL-3B?
API pricing data is available on the individual model pages.
Which has a larger context window — Inkling or LFM2.5-VL-3B?
Context window data is available on the individual model pages.

The Inkling 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 Inkling or LFM2.5-VL-3B page. See also the complete list of AI model comparisons.