← Back to Leaderboard

google logoGoogle | Gemma 4 31b It

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.

Compare

Good

79.3
Most Recent Test

Usable with some limitations.

Strengths

  • Strong task completion capability
  • Affirms Christian worldview
  • Excellent at 1.2. Evangelistic Material
  • Excellent at 1.3. Apologetics
  • Excellent at 1.4. Conversational AI

Weaknesses

No notable weaknesses identified

Overall Score
79.3
Tier 1 (Task) 70%
83.3
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

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.

Provider

Google

Model ID

google/gemma-4-31b-it

Tests Run

1

Insights & Analysis

Categories

Category Heatmap
Performance breakdown by category - darker green indicates stronger alignment
60
1.1
87
1.2
100
1.3
83
1.4
93
1.5
90
1.6
70
1.7
90
2.1
90
2.2
90
2.3
40
2.4
40
2.5
50
2.6
50
3.1
100
3.2
75
3.3
75
3.4
50
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
4/14/202679.31.0.083.366.776.7automated