Sign in

Is DeepSeek V4 Pro Preview SOTA in General LLM?#67 in General LLMRanked #67 in General LLM.

How it scores here

DeepSeek V4 Pro Preview in General LLM

Primary benchmarks

  • LMArena Text (style-controlled, overall): 1455 (CI 1451–1459) on Nov 19, 2026 (#82 of 257).

On the category's weighted score it is 39.8 points behind #1 Gemini 4 Carbon and 0.6 behind the next model up, Qwen3 7 Plus.

Nearby on the board

#ModelCategory score
64GPT-5.162.0
65Gemini 3.5 Flash Lite61.4
66Qwen3 7 Plus60.8
67DeepSeek V4 Pro Preview60.2
68Hy359.6
69GPT-5.6 Luna59.1
70Gemma 4 31B58.5
Standings

General LLM

#ModelState
1Gemini 4 CarbonCo-SOTA
1Gemini 4 ArgonCo-SOTA
1Gemini 4 NeonLeading · crown pending
1Muse WonderCo-SOTA
3Claude Opus 5.5Near-SOTA
4Claude Fable 5Near-SOTA
5Claude Fable 5.2Near-SOTA
6Claude Opus 4.6Was SOTA
7Claude Fable 5.1Was SOTA
8Claude Opus 4.7Was SOTA
9Muse Spark 1.3#9 in this category
10Gemini 3.8 FlashWas SOTA

Category page →