China’s DeepSeek has released a new open weights AI model that just topped the charts in a major performance category.
The new model, DeepSeek V3-0324, is now the highest-scoring non-reasoning model on the Artificial Analysis Index, beating out proprietary models like Gemini 2.0 Pro, Claude 3.7 Sonnet, and Grok 3.
This marks a first for open models — DeepSeek V3-0324 is the top performer in its class, ahead of well-funded closed-source competitors.
Strong Performance With Open Weights
V3-0324 scored 53 on the Artificial Analysis Index, a 7-point jump from its previous version. That increase shows DeepSeek is not just catching up to the field, but moving ahead.
The model holds its own despite no major hardware breakthroughs or dramatic changes in architecture. It uses:
- 128k context window (limited to 64k on DeepSeek’s own API)
- 671 billion total parameters
- FP8 precision
- MIT license
- Text-only output
This level of performance from an openly available model is drawing attention across the AI industry.
Not Even the Flagship Model
This release is more surprising because DeepSeek V3-0324 isn’t even the company’s top model.
According to DeepSeek, model R1 still performs better overall. A new version, R2, is reportedly on the horizon.
Anyone can try DeepSeek V3-0324 now at chat.deepseek.com.
With this latest release, DeepSeek has positioned itself as a significant global player, proving that open models can lead on performance — not just transparency.
