IBM Granite 4.2 3B vs LFM2.5-2.6B: Specs & Benchmark Comparison

IBM Granite 4.2 3B is developed by IBM, while LFM2.5-2.6B comes from Liquid AI. 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 4 published benchmarks. IBM Granite 4.2 3B leads on 3 of them, LFM2.5-2.6B on 1. The widest gaps are on AIME 2025, where IBM Granite 4.2 3B scores 78.3% against 51.9%; IFBench, where IBM Granite 4.2 3B scores 74.3% against 59.2%. Averaged across everything we track, IBM Granite 4.2 3B sits at 55.7% and LFM2.5-2.6B at 55.5%.

IBM Granite 4.2 3B is available through an API at $0.03 per million input tokens with a 131K-token context window. We do not track a hosted API for LFM2.5-2.6B, so pricing and context cannot be compared directly.

CharacteristicIBM Granite 4.2 3BLFM2.5-2.6B
CompanyIBMLiquid AI
Release DateAugust 25, 2026August 4, 2026
Parameters3B3B
MultimodalNoNo
Context (input)131K
Context (output)131K
Input Price / 1M$0.03
Output Price / 1M$0.12
Average Score55.7%55.5%
Benchmarks
AIME 202578.3%51.9%
IFBench74.3%59.2%
LiveCodeBench v669.7%59.4%
BFCL-V452.4%56.9%

Visual Benchmark Comparison

IBM Granite 4.2 3B
LFM2.5-2.6B
AIME 20250.8 vs 0.5
0.8
0.5
IFBench0.7 vs 0.6
0.7
0.6
LiveCodeBench v60.7 vs 0.6
0.7
0.6
BFCL-V40.5 vs 0.6
0.5
0.6

Verdict

IBM Granite 4.2 3B leads in 1 out of 2 comparison categories.

Overall Performance

Both models show comparable average scores: IBM Granite 4.2 3B — 0.6, LFM2.5-2.6B — 0.6.

Recency

IBM Granite 4.2 3B is newer: released 8/25/2026 vs 8/4/2026.

More About These Models

Related Comparisons

Frequently Asked Questions

Which is better for coding — IBM Granite 4.2 3B or LFM2.5-2.6B?
Direct comparison on the SWE-Bench benchmark is not available. We recommend reviewing other metrics on the comparison page.
Which model is cheaper — IBM Granite 4.2 3B or LFM2.5-2.6B?
API pricing data is available on the individual model pages.
Which has a larger context window — IBM Granite 4.2 3B or LFM2.5-2.6B?
Context window data is available on the individual model pages.

The IBM Granite 4.2 3B and LFM2.5-2.6B comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the IBM Granite 4.2 3B or LFM2.5-2.6B page. See also the complete list of AI model comparisons.