OnlySOTA

DeepSeek V4.1 Flash vs Ling 3.1 Flash

Both are SOTA right now. Each row below is one board’s call on the two, and the marked figure is the one that board places higher. No row is added to another, so there is no overall winner: the boards measure different things, and where they split, that is the finding.

Board DeepSeek V4.1 Flash Ling 3.1 Flash
Artificial Analysis LLM Leaderboard Artificial Analysis Intelligence Index 39.5 No. 28 of 374 41.1 No. 22 of 374
Arena — Agent Overall 0.040 No. 17 of 49 —
Arena — Code Overall 1620 No. 22 of 109 —
Arena — Text Overall (style control) 1474 No. 38 of 306 —

Each rank is the board’s own: the rank it publishes, or its place in its own order where it publishes none. The bar is how much of that board the model is ahead of. Scores from different boards cannot be compared.

At a glance

Developer DeepSeek InclusionAI
Weights open closed
Released ——
Price Blended Price, USD per 1M tokens (3:1 input:output) $0.52$0.45
Value: where it sits on the kill line SOTA SOTA

DeepSeek V4.1 Flash →Ling 3.1 Flash → How the kill line is drawn →

DeepSeek V4.1 Flash against the other SOTA models

Ling 3.1 Flash against the other SOTA models