DeepSeek: DeepSeek V3 Coding Benchmark
DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...
Try DeepSeek: DeepSeek V3 in Kilo Code
Experience this model with the most popular open source coding agent. Free to start, pay only for AI usage. Use in popular IDEs like VS Code, JetBrains, command line, or cloud agents.
Downloads
models supported
to Start
Access 500+ models including DeepSeek: DeepSeek V3 and many more in Kilo Code
Coding Performance
Coding benchmarks and performance metrics for development tasks
Security
Enkrypt AI red-team scores for DeepSeek: DeepSeek V3. Each value is the share of successful attacks on a 0–100 scale — lower is safer.
Lower is safer
Safety
Composite safety risk from Enkrypt red-team evaluations. Lower is safer.
NIST
Average attack success across NIST-mapped tests: bias, harm, toxicity, CBRN, and insecure code.
OWASP
Weighted average of the same tests using OWASP Top 10 for LLMs 2025 risk rankings.
Attack categories
Percentage of successful attacks in each Enkrypt red-team category.
Share of jailbreak tests that bypassed the model's safety constraints.
Share of tests that elicited biased responses.
Share of tests that produced dangerous, violent, or hateful content.
Share of tests that produced toxic or abusive content.
Share of tests that elicited chemical, biological, radiological, or nuclear assistance.
Share of tests that produced vulnerable or malicious code.
Security scores from the Enkrypt AI Safety Leaderboard · Last checked Sep 17, 2026
Real-World Usage
Real-world usage statistics from the Kilo Code community
Weekly Token Usage
No ranking data available for this model yet.
Real-world metrics from the Kilo Code Leaderboard
OpenClaw Benchmarks
PinchBench measures how DeepSeek: DeepSeek V3 performs on real OpenClaw agent tasks: multi-step execution, tool use, recovery, latency, and cost.
Average score
#45 of 50 official models
Average time
26 runs · per OpenClaw task
Average cost
Per benchmark run
Category breakdown
Best verified PinchBench v2 run by OpenClaw task family.
Top task results
Highest-scoring benchmark tasks from the same submission.
Autonomous task execution
DeepSeek: DeepSeek V3 shows emerging average success across OpenClaw-style benchmark runs, useful for recurring research, browser, and file-based automations.
Tool use and recovery
PinchBench tasks stress multi-step planning, tool calls, and judge-verified completion rather than single prompt coding snippets.
Agent workflow fit
Its deliberate average runtime and premium run cost help set expectations for long-running agents and production workflows.
Agentic benchmarks from the PinchBench Leaderboard
Pricing
Cost per 1 million tokens
Example Cost
Analyzing a 10,000 line codebase (≈40k input tokens, 10k output tokens) costs approximately $0.0206
Coding Capabilities
Features and parameters relevant to coding tasks
Coding Features
Pricing details from OpenRouter
Technical Details
Architecture and implementation specifications
- Model ID
- deepseek/deepseek-chat
- Created
- December 26, 2024
- Tokenizer
- DeepSeek
- Input Modalities
- Text
- Context Window
- 128,000 tokens
- Max Completion Tokens
- 16,000 tokens
- Input Price
- $0.26 per 1M tokens
- Output Price
- $1.03 per 1M tokens
- Content Moderation
- Disabled
Ready to try DeepSeek: DeepSeek V3?
Install Kilo Code and start using DeepSeek: DeepSeek V3 for your coding projects today. Choose from 500+ AI models with complete freedom.
Install Kilo Code
Get the extension from VS Code Marketplace, JetBrains Plugin Repository, or the CLI.
Open the model selector
Click the model name in the Kilo Code chat panel to open the selector.
Choose your model
Search or browse to find and select your preferred model.
Start coding
Use Code, Ask, Debug, or Plan mode — the model is ready immediately.