Deterministic Stack Engine

Best AI Stack for frontier agents

Coding + preference Elo for computer-use and multi-step tools.

Objective Weight Distribution

SWE-bench:35%Elo:25%Speed:15%TTFT:10%Out $:15%

Recommended PickScore 78.8 / 100

Gemini 3.7 Flash

Google · Closed flagship

swe bench p79elo p76tokens per sec p99ttft ms p99

Output: $1.875/1MSWE-bench: 72.4%

View full model fact sheet

Full Stack Leaderboard

Ranked alternatives optimized for frontier agents based on objective benchmark weighting.

#2Gemini 3 Flash(Google)

Score 76.3

swe benchP87eloP66tokens per secP96ttft msP94

Rank #2 in stackvs #1

#3DeepSeek V4 Flash(DeepSeek)

Score 73.3

swe benchP74eloP61tokens per secP81ttft msP75

Rank #3 in stackvs #1

#4GLM-5.3(Zhipu)

Score 71.4

swe benchP91eloP86tokens per secP45ttft msP38

Rank #4 in stackvs #1

#5Gemini 3.6 Flash(Google)

Score 71.3

swe benchP71eloP68tokens per secP98ttft msP96

Rank #5 in stackvs #1

#6Gemini 3.6 Pro(Google)

Score 71.2

swe benchP85eloP91tokens per secP58ttft msP58

Rank #6 in stackvs #1

#7OpenAI: o3 Mini(OpenAI)

Score 70.2

swe benchP96eloP88tokens per secP49ttft msP26

Rank #7 in stackvs #1

#8Claude Sonnet 5(Anthropic)

Score 70.1

swe benchP83eloP84tokens per secP69ttft msP70

Rank #8 in stackvs #1

#9GPT-5.6 Terra(OpenAI)

Score 67.0

swe benchP69eloP81tokens per secP74ttft msP77

Rank #9 in stackvs #1

#10GPT-5.6 Sol(OpenAI)

Score 66.5

swe benchP94eloP96tokens per secP34ttft msP35

Rank #10 in stackvs #1