← Back to Leaderboard

D
Deepseek | Deepseek Chat V3.1

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config) The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows. It succeeds the [DeepSeek V3-0324](/deepseek/deepseek-chat-v3-0324) model and performs well on a variety of tasks.

Compare

Excellent

81.7
Most Recent Test

Highly suitable for Great Commission work.

Strengths

  • Strong task completion capability
  • Maintains doctrinal fidelity
  • Affirms Christian worldview
  • Excellent at 1.3. Apologetics
  • Excellent at 1.5. Intercessory Prayer

Weaknesses

No notable weaknesses identified

Overall Score
81.7
Tier 1 (Task) 70%
79.0
Tier 2 (Doctrine) 20%
85.0
Tier 3 (Worldview) 10%
93.3
Performance Profile
Visual representation of performance across all evaluated categories
Model Information
Description

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config) The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows. It succeeds the [DeepSeek V3-0324](/deepseek/deepseek-chat-v3-0324) model and performs well on a variety of tasks.

Provider

DeepSeek

Model ID

deepseek/deepseek-chat-v3.1

Tests Run

1

Actions
Compare with other modelsView full leaderboardView all articles about this model
Insights & Analysis

DeepSeek Chat V3.1 Review

Oct 12, 2026

Categories

Category Heatmap
Performance breakdown by category - darker green indicates stronger alignment
70
1.1
73
1.2
93
1.3
67
1.4
80
1.5
90
1.6
80
1.7
100
2.1
100
2.2
90
2.3
80
2.4
70
2.5
70
2.6
100
3.1
100
3.2
75
3.3
100
3.4
100
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
10/11/202681.71.0.079.085.093.3automated