← Back to Leaderboard

Q
Qwen | Qwen3.6 35b A3b

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated DeltaNet linear attention with standard gated attention layers, enabling efficient inference at a fraction of the compute cost. The model supports a 262K token native context window (extensible to 1M via YaRN) and accepts text, image, and video inputs. It includes integrated thinking mode with reasoning traces preserved across multi-turn conversations, function calling, and structured output. Released under the Apache 2.0 license.

Compare

Good

68.3
Most Recent Test

Usable with some limitations.

Strengths

  • Affirms Christian worldview
  • Excellent at 1.3. Apologetics
  • Excellent at 1.6. Problematic Vocabulary
  • Excellent at 1.7. Difficult Passages
  • Excellent at 2.1. Exclusivity of Jesus

Weaknesses

  • Struggles with 1.1. Missiological Research
  • Struggles with 3.5. Universal Sinfulness
Overall Score
68.3
Tier 1 (Task) 70%
67.6
Tier 2 (Doctrine) 20%
66.7
Tier 3 (Worldview) 10%
76.7
Performance Profile
Visual representation of performance across all evaluated categories
Model Information
Description

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated DeltaNet linear attention with standard gated attention layers, enabling efficient inference at a fraction of the compute cost. The model supports a 262K token native context window (extensible to 1M via YaRN) and accepts text, image, and video inputs. It includes integrated thinking mode with reasoning traces preserved across multi-turn conversations, function calling, and structured output. Released under the Apache 2.0 license.

Provider

Qwen

Model ID

qwen/qwen3.6-35b-a3b

Tests Run

1

Insights & Analysis

Categories

Category Heatmap
Performance breakdown by category - darker green indicates stronger alignment
17
1.1
67
1.2
90
1.3
73
1.4
67
1.5
80
1.6
80
1.7
90
2.1
80
2.2
70
2.3
40
2.4
50
2.5
70
2.6
50
3.1
100
3.2
100
3.3
50
3.4
25
3.5
100
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
DateScoreVersionTier 1 (Task)Tier 2 (Gospel)Tier 3 (Worldview)Trust Tier
10/11/202668.31.0.067.666.776.7automated