Deterministic Stack Engine

Best AI Stack for cheap coding agents

SWE-bench first, then price. For CI bots and repo agents that cannot burn Opus prices.

Objective Weight Distribution

SWE-bench:40%Out $:35%Speed:15%Code Elo:10%

Recommended PickScore 76.2 / 100

DeepSeek V4 Flash

DeepSeek · Open weights

swe bench p74output price per m p83tokens per sec p81elo coding p54

Output: $0.28/1MSWE-bench: 71.2%

View full model fact sheet

Full Stack Leaderboard

Ranked alternatives optimized for cheap coding agents based on objective benchmark weighting.

#2Gemini 3.7 Flash(Google)

Score 71.1

swe benchP79output price per mP49tokens per secP99elo codingP75

Rank #2 in stackvs #1

#3MiniMax M2.5(MiniMax)

Score 70.8

swe benchP87output price per mP64tokens per secP45elo codingP68

Rank #3 in stackvs #1

#4GLM-5.3(Zhipu)

Score 69.8

swe benchP91output price per mP50tokens per secP45elo codingP91

Rank #4 in stackvs #1

#5Gemini 3 Flash(Google)

Score 67.0

swe benchP87output price per mP37tokens per secP96elo codingP48

Rank #5 in stackvs #1

#6Yi-Lightning(01.AI)

Score 66.6

swe benchP51output price per mP89tokens per secP76elo codingP37

Rank #6 in stackvs #1

#7OpenAI: o3 Mini(OpenAI)

Score 65.5

swe benchP96output price per mP31tokens per secP49elo codingP89

Rank #7 in stackvs #1

#8Gemini 2.0 Flash Thinking(Google)

Score 65.3

swe benchP58output price per mP77tokens per secP66elo codingP52

Rank #8 in stackvs #1

#9DeepSeek V4 Pro(DeepSeek)

Score 63.7

swe benchP76output price per mP65tokens per secP21elo codingP74

Rank #9 in stackvs #1

#10Gemini 3.6 Pro(Google)

Score 60.6

swe benchP85output price per mP28tokens per secP58elo codingP81

Rank #10 in stackvs #1