← Back to Leaderboard
QQwen | Qwen3.5 35b A3b
The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall performance is comparable to that of the Qwen3.5-27B.
Fair
46.0
Most Recent TestSignificant guardrail issues may impede work.
Strengths
- Excellent at 2.2. Universality of Sin
- Excellent at 3.2. Historical Jesus
Weaknesses
- Limited task completion capability
- Weak doctrinal alignment
- Resists worldview confession
- Struggles with 1.1. Missiological Research
- Struggles with 2.4. Lordship of Jesus
Overall Score
46.0
Tier 1 (Task) 70%
49.0
Tier 2 (Doctrine) 20%
40.0
Tier 3 (Worldview) 10%
36.7
Performance Profile
Visual representation of performance across all evaluated categories
Model Information
Description
The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall performance is comparable to that of the Qwen3.5-27B.
Provider
Qwen
Model ID
qwen/qwen3.5-35b-a3b
Tests Run
1
Categories
Category Heatmap
Performance breakdown by category - darker green indicates stronger alignment
33
1.1
57
1.2
43
1.3
60
1.4
43
1.5
57
1.6
50
1.7
70
2.1
90
2.2
40
2.3
20
2.4
0
2.5
20
2.6
0
3.1
100
3.2
25
3.3
50
3.4
25
3.5
33
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 |
|---|---|---|---|---|---|---|
| 10/11/2026 | 46.0 | 1.0.0 | 49.0 | 40.0 | 36.7 | automated |