← Back to Leaderboard
Liquid | Lfm 2.5 24b A2b
LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid recommends pairing it with retrieval or web search for knowledge-heavy tasks.
Good
69.3
Most Recent TestUsable with some limitations.
Strengths
- Excellent at 1.4. Conversational AI
- Excellent at 1.6. Problematic Vocabulary
- Excellent at 2.2. Universality of Sin
- Excellent at 3.2. Historical Jesus
- Excellent at 3.3. The Crucifixion
Weaknesses
- Struggles with 2.6. Burden to Make Disciples
- Struggles with 3.5. Universal Sinfulness
Overall Score
69.3
Tier 1 (Task) 70%
72.9
Tier 2 (Doctrine) 20%
56.7
Tier 3 (Worldview) 10%
70.0
Performance Profile
Visual representation of performance across all evaluated categories
Model Information
Description
LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid recommends pairing it with retrieval or web search for knowledge-heavy tasks.
Provider
Liquid
Model ID
liquid/lfm-2.5-24b-a2b
Tests Run
1
Categories
Category Heatmap
Performance breakdown by category - darker green indicates stronger alignment
53
1.1
73
1.2
77
1.3
83
1.4
77
1.5
83
1.6
63
1.7
40
2.1
100
2.2
60
2.3
70
2.4
50
2.5
20
2.6
50
3.1
100
3.2
88
3.3
75
3.4
25
3.5
67
3.6
Low
High
Category Breakdown (Bar Chart)
Performance across different categories
1.x = Task Capability2.x = Gospel Core3.x = Worldview Confession
Recent Tests
Recent Test Runs
| Date | Score | Version | Tier 1 (Task) | Tier 2 (Gospel) | Tier 3 (Worldview) | Trust Tier |
|---|---|---|---|---|---|---|
| 10/14/2026 | 69.3 | 1.0.0 | 72.9 | 56.7 | 70.0 | automated |