Hy3 vs LFM2.5-2.6B: Specs & Benchmark Comparison

Hy3 is developed by Tencent, while LFM2.5-2.6B comes from Liquid AI. Hy3 was released in July 2026, and LFM2.5-2.6B followed a month later in August 2026. Hy3 is the larger model at roughly 295 billion parameters, against 3 billion for LFM2.5-2.6B.

We have 31 benchmark results for Hy3 and 8 benchmark results for LFM2.5-2.6B, but they overlap on a single test: Claw-Eval, where Hy3 scores 68.5% against 62.8%.

CharacteristicHy3LFM2.5-2.6B
CompanyTencentLiquid AI
Release DateJuly 6, 2026August 4, 2026
Parameters295B3B
MultimodalNoNo
Average Score57.1%55.5%
Benchmarks
Claw-Eval68.5%62.8%

Visual Benchmark Comparison

Hy3
LFM2.5-2.6B
Claw-Eval0.7 vs 0.6
0.7
0.6

Verdict

LFM2.5-2.6B leads in 1 out of 2 comparison categories.

Overall Performance

Both models show comparable average scores: Hy3 — 0.6, LFM2.5-2.6B — 0.6.

Recency

LFM2.5-2.6B is newer: released 8/4/2026 vs 7/6/2026.

More About These Models

Related Comparisons

Frequently Asked Questions

Which is better for coding — Hy3 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 — Hy3 or LFM2.5-2.6B?
API pricing data is available on the individual model pages.
Which has a larger context window — Hy3 or LFM2.5-2.6B?
Context window data is available on the individual model pages.

The Hy3 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 Hy3 or LFM2.5-2.6B page. See also the complete list of AI model comparisons.