AI Model Timeline

Tracking the accelerating release frequency of frontier AI models.

DeepSeek-V4-Pro-0813

DeepSeek·

LLMsopen-weightFrontier

Overview

General-availability build of DeepSeek-V4-Pro. Identical 1.6T total / 49B active MoE architecture and size as the April preview — re-post-trained, with the gains concentrated in agentic and software-engineering tasks. 1M-token context, MIT license.

Capabilities and innovations

1.6T total / 49B active MoE1M token context windowThree reasoning effort modes (incl. Think Max)MIT licenseHybrid attention: CSA + HCAManifold-Constrained Hyper-ConnectionsRe-post-training of the April preview checkpoint

Benchmarks

BenchmarkScoreSource
GPQA Diamond92.83%third party
GPQA Diamond 92.83%, Artificial Analysis, reasoning max effort, measured on the 0813 build (April preview: 89.4 on vals.ai, 90.1 vendor). Same source lineage as the V4-Flash-0731 entry.
Humanity’s Last Exam (no tools)39.34%third party
HLE 39.34% no-tools, Artificial Analysis Intelligence Index component, max effort (April preview: 37.7 vendor).
SWE-bench Verified96.4%independent
SWE-bench Verified 96.40 (± 0.83), vals.ai, max effort (April preview: 77.4 on the same harness). Era-1 benchmark, near saturation — recorded for continuity, not ranked.
Terminal-Bench 2.x78.65%third party
Terminal-Bench 2.1 78.65%, Artificial Analysis, max effort. Measurements diverge widely on this build: vals.ai reports 54.68 (± 1.50) and DeepSeek self-reports 87.9 on the same benchmark version. Artificial Analysis is kept as primary for continuity with the V4-Flash-0731 entry. Version 2.1, not comparable to the 2.0 score recorded for the April preview.
  • SWE-bench Pro: independent evaluation pending — The April preview checkpoint scored 55.4; no re-run published for the 0813 build.
  • MMLU-Pro: independent evaluation pending — The April preview checkpoint scored 87.5 (vendor) / 87.25 (vals.ai); vals.ai has not yet re-run MMLU Pro on the 0813 build.
  • MMMU-Pro: not reported by the vendor

Architecture and hardware

Parameters
1600B total, 49B active per token (MoE)
Estimated VRAM at Q4
~920 GB, Frontier class
Quantization formats
FP8, GGUF
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.