LongCat

LongCat 2.0

Jun 29, 2026ReasoningOpen weightsModels.dev

Compare

Intelligence

19.1

#259 of 744Rank 259 of 744 measured models

Coding

45.3

#137 of 298Rank 137 of 298 measured models

Output speed

67.2 t/s

#258 of 403Rank 258 of 403 measured models

Price/1M

$1.30

#412 of 659Rank 412 of 659 measured models

Context window

1M

#84 of 1199Rank 84 of 1199 measured models

Cost per task

$0.146

#65 of 193Rank 65 of 193 measured models

LongCat 2.0 scores 19.1 on the Artificial Analysis Intelligence Index, ranking 259th of 744 measured models. The closest models on this index are Step 3.7 Flash (19.5), Claude 4.5 Sonnet (19.3), and Qwen3.5 35B A3B (19.3). At $1.30 per million tokens (3:1 input/output blended price), it is cheaper than Claude 4.5 Sonnet ($6), more expensive than Step 3.7 Flash ($0.438) and Qwen3.5 35B A3B ($0.688). With an output speed of 67.2 t/s, it is faster than Claude 4.5 Sonnet (41 t/s), slower than Step 3.7 Flash (185 t/s) and Qwen3.5 35B A3B (147 t/s).