AI Model Timeline

Tracking the accelerating release frequency of frontier AI models.

DeepSeek-V3.1

DeepSeek·

LLMsopen-weightcloud + localFrontier

Overview

Incremental update with better instruction following.

Capabilities and innovations

Instruction followingLong contextMath improvements

Benchmarks

BenchmarkScoreSource
GPQA Diamond81.4%unsourced
Humanity’s Last Exam (no tools)25.1%unsourced
SWE-bench Verified54.7%unsourced
MMLU87.6%unsourced
  • SWE-bench Pro: not reported by the vendor
  • MMLU-Pro: not reported by the vendor
  • Terminal-Bench 2.x: benchmark did not exist at release
  • MMMU-Pro: benchmark did not exist at release

Architecture and hardware

Parameters
671B total, 37B active per token (MoE)
Estimated VRAM at Q4
~386 GB, Frontier class

Links

More from DeepSeek

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