Model comparison
LFM2.5-24B-A2B vs Hunyuan Hy3
- Input
- $0.10
- Output
- $1.00
- Context
- 128K
- Released
- 2026-10-13
- Input
- ¥1.00
- Output
- ¥4.00
- Context
- 256K
- Released
- 2026-07-06
Hunyuan Hy3 scores higher on 2 of the 2 benchmarks both models report; Hunyuan Hy3 has the larger context window (256K vs 128K).
Specs and pricing side by side
| Spec | LFM2.5-24B-A2B | Hunyuan Hy3 |
|---|---|---|
| Maker | Liquid AI | Tencent |
| Released | 2026-10-13 | 2026-07-06 |
| Context window | 128K | 256K |
| Input price | $0.10 | ¥1.00 |
| Output price | $1.00 | ¥4.00 |
| Parameters | 24.0B total · 2.45B active | 295B total · 21B active |
| License | LFM Open License v1.0 | Apache-2.0 |
| Weights | Open weights | Open weightssame |
| Modalities | Text | Textsame |
Not published by either maker: max output, knowledge cutoff.
Benchmarks both models report
| Benchmark | LFM2.5-24B-A2B | Hunyuan Hy3 |
|---|---|---|
| GPQA Diamond | 74.42% | 90.4% |
| SWE-Bench Verified | 51% | 78% |
Scores are as published by each maker or its cited source; harness, reasoning effort and date can differ between rows, so treat small gaps as ties. Sources are listed on each model page.
Which one should you pick?
Pick LFM2.5-24B-A2B if…
- Your use case is: running a private coding or personal agent locally on a Mac or AMD laptop through an OpenAI-compatible server and a harness such as Hermes, OpenClaw or Pi.
Pick Hunyuan Hy3 if…
- You care about GPQA Diamond, SWE-Bench Verified (it scores higher on 2 shared benchmarks).
- You need the longer context (256K vs 128K).
- Your use case is: self-hosted agentic coding, tool use and terminal automation via vLLM or SGLang recipes.
FAQ
Which is better, LFM2.5-24B-A2B or Hunyuan Hy3?
Hunyuan Hy3 scores higher on 2 of the 2 benchmarks both models report; Hunyuan Hy3 has the larger context window (256K vs 128K). The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.
What are the context windows of LFM2.5-24B-A2B and Hunyuan Hy3?
LFM2.5-24B-A2B offers 128K; Hunyuan Hy3 offers 256K.
Is LFM2.5-24B-A2B newer than Hunyuan Hy3?
LFM2.5-24B-A2B was released 2026-10-13; Hunyuan Hy3 was released 2026-07-06.