DeepSeek · DeepSeek V4
DeepSeek V4 Pro (0813)
DeepSeek's larger open-weight text MoE (1.6T total / 49B active, 1M context), GA since the 0813 post-training update, for harder coding and agent work.
- AA Intelligence
- 36#37 of 151
- Input / output per 1M
- $1.32/ $3.96
- Output speed
- 89tok/s
- Context window
- 1M tokens
Composite indexes
- Artificial Analysis Intelligence Index#37 of 15136
Leader: Claude Opus 5.5 at 58
Coding
- Terminal-Bench 4.0#31 of 9614.1%12.4%
Leader: Claude Sonnet 5.5 at 70.6%
- Terminal-Bench 2.x#27 of 10587.9%78.7%
Leader: Claude Fable 5.1 at 91.4%
- SciCode#40 of 10051%
Leader: Claude Opus 5.5 at 66.9%
Agents and tool use
- GDPval-AA#28 of 1091441
Leader: Muse Wonder Full at 1857
Reasoning and knowledge
- GPQA Diamond#18 of 14492.8%92.4%
Leader: GPT-6 Astra at 96.1%
- Humanity’s Last Exam#35 of 15360%42.7%41%
Leader: Claude Sonnet 5.5 at 64.5%
- CritPt#23 of 14418%
Leader: Muse Wonder Full at 33%
Vision and long context
- AA Long Context Reasoning#30 of 14480.3%
Leader: Kimi K3 at 88.7%
Human preference
- LMArena Text#26 of 571463
Leader: Gemini 4 Argon at 1525
- LMArena WebDev#27 of 581581
Leader: Claude Opus 5.5 at 1818
Other published results
| Result | Score | Reported by | Source |
|---|---|---|---|
| DeepSWE | 62.7% | vendor | DeepSeek-V4-Pro-0813 model card (Hugging Face) ↗ |
| Agents' Last Exam | 25.7% | vendor | DeepSeek-V4-Pro-0813 model card (Hugging Face) ↗ |
| Toolathlon-Verified | 74.1% | vendor | DeepSeek-V4-Pro-0813 model card (Hugging Face) ↗ |
| NL2Repo | 61.5 score | vendor | DeepSeek-V4-Pro-0813 model card (Hugging Face) ↗ |
| CyberGym | 83.3% | vendor | DeepSeek-V4-Pro-0813 model card (Hugging Face) ↗ |
| AutomationBench (Public) | 31.8% | vendor | DeepSeek-V4-Pro-0813 model card (Hugging Face) ↗ |