DeepSeek V3.1 by DeepSeek demonstrates strong general intelligence, competitive pricing. View detailed benchmark data including scores across coding, math, reasoning, speed, and cost metrics.
General Benchmarks
Coding Benchmarks
Reasoning Benchmarks
Speed Benchmarks
Cost Benchmarks
Context Benchmarks
DeepSeek V3.1 — Benchmark Scores Overview
Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).
Compare DeepSeek V3.1 With
DeepSeek V3.1 — Frequently Asked Questions
How intelligent is DeepSeek V3.1?
DeepSeek V3.1 scores 1340 on the Chatbot Arena ELO rating, making it a mid-tier AI model. This score is based on blind head-to-head human preference voting.
How much does DeepSeek V3.1 cost?
DeepSeek V3.1 costs $0.14 per 1M input tokens and $0.28 per 1M output tokens. This makes it one of the more affordable models.
How fast is DeepSeek V3.1?
DeepSeek V3.1 generates output at 65 tokens per second, which is slower, prioritizing quality over speed compared to other models. The time to first token is 450 ms.
How good is DeepSeek V3.1 at coding?
DeepSeek V3.1 achieves 46.0% on SWE-bench Verified, demonstrating moderate real-world software engineering capability. This benchmark tests the model's ability to resolve actual GitHub issues.
How good is DeepSeek V3.1 at math and reasoning?
DeepSeek V3.1 scores 82.0% on the MATH benchmark (competition-level mathematics). It also achieves 55.0% on GPQA Diamond, a graduate-level science reasoning benchmark.
What is the context window of DeepSeek V3.1?
DeepSeek V3.1 has a context window of 131K tokens. This determines how much text, conversation history, and code the model can process in a single request.
Who created DeepSeek V3.1?
DeepSeek V3.1 was created by DeepSeek. It is classified as a open source model in the AI Value Index.
Is DeepSeek V3.1 open source?
Yes, DeepSeek V3.1 is an open-source model. The model weights are publicly available for download and self-hosting.