DeepSeek V4 Pro Scores Below Kimi K3 and Qwen

bindureddy · x · 2026-08-13

According to shared evaluation results, DeepSeek V4 Pro has scored lower than Kimi K3 and Qwen.

Kimi K3 remains the current leader among open-source models, a position that may hold until the release of GLM 5.5 later this month. The author suggests that DeepSeek might require a completely new pre-training run to catch up.

Related event: DeepSeek-V4-Pro Officially Released with Enhanced Agent Capabilities and Peak Pricing(48 posts)→

Original post →

More from Models

Models channel →