DeepSeek AI · Reasoning
DeepSeek-V4-Flash-0731
Production release retrains the April preview with an overhauled post-training pipeline rather than scaling up — 284B total parameters, 13B activated per token via MoE, 1M-token context, plus an attached speculative-decoding module (304B repo size). Beats DeepSeek-V4-Pro Preview on agentic evals: 82.7 vs 72.1 on Terminal-Bench 2.1, 54.4 vs 12.8 on DeepSWE. MIT-licensed.
Open the source ↗Similar Language Models releases
- Groot-280B-A16B-261023
GrootTeam · Open reasoning MoE · Week 45, 2026
- Apex-35B-V1.0
Apex Intelligence · Research automation LLM · Week 45, 2026
- Kimi K3.1 Pro
Moonshot AI · Open-Weight Frontier · Week 44, 2026
- DeepSeek-V4.1-Flash-1017
DeepSeek · Open-Weight LLM · Week 44, 2026
- Ornith 1.0
DeepReinforce · Code Generation · Week 26, 2026
- Qwen3-Coder
Alibaba Qwen Team · Code Generation · Week 24, 2025
More from DeepSeek AI
- DeepSeek vision API
DeepSeek AI · Visual Understanding · Week 34, 2026
- DeepSeek Harness (dsh)
DeepSeek AI · Agent Framework · Week 33, 2026
- DeepSeek-V4-Pro-0813
DeepSeek AI · MoE Architecture · Week 33, 2026
- DeepSeek-OCR-2
DeepSeek AI · OCR & Document · Week 5, 2026
- DeepSeek-Math-V2
DeepSeek AI · Reasoning · Week 49, 2025
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.