← All leaderboards
The verdict
DeepSeek-V4-Pro appears in 1 AI-ranked category — best position #2 for open-weight llm.
GPT #2Claude —Gemini #1Grok —
Offers frontier-level intelligence for coding, reasoning, and agentic workflows with a dual Thinking/Non-Thinking mode under a permissive MIT license, while dramatically reducing KV cache usage.
GPT Near-tied with GLM-5.2, with exceptional reasoning, coding, long-context processing, agentic execution, a permissive license, and unusually strong API value.
Where DeepSeek-V4-Pro falls short, per the models
- GPT The enormous 1.6T-parameter model is unrealistic for typical practitioners to self-host.
- Gemini Its massive 1.6T total parameter size makes local self-hosting extremely resource-intensive, requiring high-end multi-GPU cluster infrastructure.
Top alternatives per the models: GLM-5.2 · DeepSeek-V3.2 · Kimi K2.5 · Llama 4 Maverick
Rankings are computed from what the models answer, re-polled weekly · raw reasoning shown verbatim · methodology