Liquid AI · LFM2
LFM2 24B A2B
Liquid AI's largest LFM2 MoE (23.8B total / 2.3B active) for efficient local inference.
- AA Intelligence
- 5.9#132 of 142
- Price
- Self-host
- Output speed
- —
- Context window
- 33K tokens
Composite indexes
- Artificial Analysis Intelligence Index#132 of 1426
Leader: Claude Opus 5.5 at 58
Agents and tool use
- τ²-Bench#80 of 8811.1%
Leader: GLM-5.2 at 99.1%
Reasoning and knowledge
- GPQA Diamond#127 of 14247.4%
Leader: GPT-6 Astra at 96.1%
- Humanity’s Last Exam#138 of 1474.2%
Leader: Claude Opus 5.5 at 61.4%
- CritPt#130 of 1390%
Leader: GPT-5.6 Sol at 32.3%
Vision and long context
- AA Long Context Reasoning#136 of 1390%
Leader: Kimi K3 at 88.7%
Other published results
| Result | Score | Reported by | Source |
|---|---|---|---|
| Terminal-Bench Hard (AA) · non-reasoning | 0% | independent | Artificial Analysis: LFM2 24B A2B ↗ |
| IFBench · non-reasoning | 45.9% | independent | Artificial Analysis: LFM2 24B A2B ↗ |
| AA-Omniscience Index · non-reasoning | -58.1 index | independent | Artificial Analysis: LFM2 24B A2B ↗ |