← Back to Leaderboard
Kt | Midm K 3.0 Pro
Mi:dm K 3.0 Pro is a Mixture-of-Experts reasoning model from KT, with 120B total and 12B active parameters. It uses a hybrid architecture that mixes Mamba, MoE and attention layers.
Fair
43.3
Most Recent TestSignificant guardrail issues may impede work.
Strengths
No notable strengths identified
Weaknesses
- Limited task completion capability
- Weak doctrinal alignment
- Struggles with 1.1. Missiological Research
- Struggles with 1.7. Difficult Passages
- Struggles with 2.3. Reality of Judgment
Overall Score
43.3
Tier 1 (Task) 70%
44.8
Tier 2 (Doctrine) 20%
30.0
Tier 3 (Worldview) 10%
60.0
Performance Profile
Visual representation of performance across all evaluated categories
Model Information
Description
Mi:dm K 3.0 Pro is a Mixture-of-Experts reasoning model from KT, with 120B total and 12B active parameters. It uses a hybrid architecture that mixes Mamba, MoE and attention layers.
Provider
Kt
Model ID
kt/midm-k-3.0-pro
Tests Run
1
Categories
Category Heatmap
Performance breakdown by category - darker green indicates stronger alignment
23
1.1
53
1.2
60
1.3
53
1.4
47
1.5
60
1.6
17
1.7
40
2.1
60
2.2
20
2.3
40
2.4
20
2.5
0
2.6
50
3.1
75
3.2
75
3.3
75
3.4
0
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 |
|---|---|---|---|---|---|---|
| 11/11/2026 | 43.3 | 1.0.0 | 44.8 | 30.0 | 60.0 | automated |