← Back to Leaderboard
Tencent | Hy4
The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity tasks. It also introduces visual understanding for the first time.
Fair
51.7
Most Recent TestSignificant guardrail issues may impede work.
Strengths
- Excellent at 3.3. The Crucifixion
Weaknesses
- Limited task completion capability
- Struggles with 1.7. Difficult Passages
- Struggles with 3.5. Universal Sinfulness
Overall Score
51.7
Tier 1 (Task) 70%
48.1
Tier 2 (Doctrine) 20%
56.7
Tier 3 (Worldview) 10%
66.7
Performance Profile
Visual representation of performance across all evaluated categories
Model Information
Description
The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity tasks. It also introduces visual understanding for the first time.
Provider
Tencent
Model ID
tencent/hy4
Tests Run
1
Categories
Category Heatmap
Performance breakdown by category - darker green indicates stronger alignment
40
1.1
50
1.2
63
1.3
63
1.4
40
1.5
53
1.6
27
1.7
70
2.1
60
2.2
50
2.3
60
2.4
40
2.5
60
2.6
50
3.1
75
3.2
100
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 |
|---|---|---|---|---|---|---|
| 11/4/2026 | 51.7 | 1.0.0 | 48.1 | 56.7 | 66.7 | automated |