AI Model Timeline

Tracking the accelerating release frequency of frontier AI models.

DeepSeek-V3.1

DeepSeek·

LLMsopen-weightFrontier

Overview

Incremental update with better instruction following and improved benchmark scores across the board.

Capabilities and innovations

671B total / 37B active parameters (MoE)Improved instruction following128K context windowEnhanced coding and reasoningRefined RLHF alignmentImproved multi-turn consistencyBetter long-context utilization

Benchmarks

BenchmarkScoreSource
GPQA Diamond81.4%unsourced
Humanity’s Last Exam (no tools)25.1%unsourced
SWE-bench Verified54.7%unsourced
MMLU87.6%unsourced

Architecture and hardware

Parameters
671B total, 37B active per token (MoE)
Estimated VRAM at Q4
~386 GB, Frontier class
Quantization formats
GGUF, GPTQ, FP8
Recommended runtime
vLLM
License
MIT

Links

More from DeepSeek

Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.