r1/04-prompt-brief
slop
9tells
4 distinct · aes 8 · floor 1
model=deepseek-v4.1-flash · skills=none · prompt=brief · stack=plain · feedback=blind · subject=saas
default_fonts, missing_og, numbered_steps, uppercase_labels
r1/02-skill-no-slop
clean
0tells
0 distinct · aes 0 · floor 0
model=deepseek-v4.1-flash · skills=no-slop · prompt=minimal · stack=plain · feedback=blind · subject=saas
r1/00-baseline
slop
17tells
6 distinct · aes 17 · floor 0
model=deepseek-v4.1-flash · skills=none · prompt=minimal · stack=plain · feedback=blind · subject=saas
colored_glows, distinct_radius_values, hidden_without_js, hover_lift_effects, numbered_steps, uppercase_labels
r1/01-skill-frontend-design
slop
26tells
8 distinct · aes 25 · floor 1
model=deepseek-v4.1-flash · skills=frontend-design · prompt=minimal · stack=plain · feedback=blind · subject=saas
default_fonts, distinct_radius_values, hidden_without_js, hover_lift_effects, missing_og, nested_cards, numbered_steps, uppercase_labels
r1/08-model-gpt-6-luna
clean
0tells
0 distinct · aes 0 · floor 0
model=gpt-6-luna · skills=none · prompt=minimal · stack=plain · feedback=blind · subject=saas
r1/03-skill-both
clean
0tells
0 distinct · aes 0 · floor 0
model=deepseek-v4.1-flash · skills=frontend-design,no-slop · prompt=minimal · stack=plain · feedback=blind · subject=saas
r1/06-stack-tailwind
slop
7tells
2 distinct · aes 7 · floor 0
model=deepseek-v4.1-flash · skills=none · prompt=minimal · stack=tailwind · feedback=blind · subject=saas
distinct_radius_values, numbered_steps
r1/07-stack-react-shadcn
review
1tells
1 distinct · aes 1 · floor 0
model=deepseek-v4.1-flash · skills=none · prompt=minimal · stack=react · feedback=blind · subject=saas
r1/05-prompt-full
clean
0tells
0 distinct · aes 0 · floor 0
model=deepseek-v4.1-flash · skills=none · prompt=full · stack=plain · feedback=blind · subject=saas
r1/12-model-muse-spark-1.3
slop
14tells
5 distinct · aes 13 · floor 1
model=muse-spark-1.3-contributor · skills=none · prompt=minimal · stack=plain · feedback=blind · subject=saas
distinct_radius_values, missing_og, nested_cards, numbered_steps, uppercase_labels
r1/11-model-mimo-v2.6-flash
slop
23tells
5 distinct · aes 22 · floor 1
model=mimo-v2.6-flash · skills=none · prompt=minimal · stack=plain · feedback=blind · subject=saas
distinct_radius_values, missing_og, nested_cards, numbered_steps, uppercase_labels
r1/14-subject-lighthouse
slop
23tells
7 distinct · aes 23 · floor 0
model=deepseek-v4.1-flash · skills=none · prompt=minimal · stack=plain · feedback=blind · subject=lighthouse
colored_glows, contrast_failures, distinct_radius_values, hero_emphasis, hover_lift_effects, numbered_steps, uppercase_labels
r1/09-model-glm-5.3-flash
slop
6tells
5 distinct · aes 5 · floor 1
model=glm-5.3-flash · skills=none · prompt=minimal · stack=plain · feedback=blind · subject=saas
default_fonts, hero_emphasis, hidden_without_js, hover_lift_effects, missing_og
r1/13-feedback-revise
slop
9tells
3 distinct · aes 9 · floor 0
model=deepseek-v4.1-flash · skills=none · prompt=minimal · stack=plain · feedback=revise · subject=saas
default_fonts, numbered_steps, uppercase_labels
r1/10-model-qwen3.8-flash
review
0tells
0 distinct · aes 0 · floor 0
model=qwen3.8-flash · skills=none · prompt=minimal · stack=plain · feedback=blind · subject=saas
r2/none-hotsauce-1
slop
12tells
4 distinct · aes 12 · floor 0
arm=none · subject=hotsauce · rep=1 · model=deepseek-v4.1-flash
hero_emphasis, hover_lift_effects, numbered_steps, uppercase_labels
r2/none-hotsauce-2
slop
11tells
4 distinct · aes 11 · floor 0
arm=none · subject=hotsauce · rep=2 · model=deepseek-v4.1-flash
hero_emphasis, hover_lift_effects, numbered_steps, uppercase_labels
r2/none-hotsauce-3
slop
16tells
5 distinct · aes 16 · floor 0
arm=none · subject=hotsauce · rep=3 · model=deepseek-v4.1-flash
distinct_radius_values, hero_emphasis, hover_lift_effects, numbered_steps, uppercase_labels
r2/none-lighthouse-1
clean
0tells
0 distinct · aes 0 · floor 0
arm=none · subject=lighthouse · rep=1 · model=deepseek-v4.1-flash
r2/none-lighthouse-2
slop
16tells
6 distinct · aes 16 · floor 0
arm=none · subject=lighthouse · rep=2 · model=deepseek-v4.1-flash
colored_glows, contrast_failures, distinct_radius_values, hero_emphasis, numbered_steps, uppercase_labels
r2/none-lighthouse-3
slop
26tells
9 distinct · aes 26 · floor 0
arm=none · subject=lighthouse · rep=3 · model=deepseek-v4.1-flash
colored_glows, contrast_failures, default_fonts, distinct_radius_values, hero_emphasis, hidden_without_js, hover_lift_effects, numbered_steps, uppercase_labels
r2/none-saas-1
review
1tells
1 distinct · aes 1 · floor 0
arm=none · subject=saas · rep=1 · model=deepseek-v4.1-flash
r2/none-saas-2
review
1tells
1 distinct · aes 1 · floor 0
arm=none · subject=saas · rep=2 · model=deepseek-v4.1-flash
r2/none-saas-3
slop
7tells
2 distinct · aes 7 · floor 0
arm=none · subject=saas · rep=3 · model=deepseek-v4.1-flash
numbered_steps, uppercase_labels
r2/noslop-hotsauce-1
slop
5tells
2 distinct · aes 5 · floor 0
arm=noslop · subject=hotsauce · rep=1 · model=deepseek-v4.1-flash
numbered_steps, uppercase_labels
r2/noslop-hotsauce-2
no build
--tells
not scanned
arm=noslop · subject=hotsauce · rep=2 · model=deepseek-v4.1-flash
no screenshot
r2/noslop-hotsauce-3
clean
0tells
0 distinct · aes 0 · floor 0
arm=noslop · subject=hotsauce · rep=3 · model=deepseek-v4.1-flash
r2/noslop-lighthouse-1
clean
0tells
0 distinct · aes 0 · floor 0
arm=noslop · subject=lighthouse · rep=1 · model=deepseek-v4.1-flash
r2/noslop-lighthouse-2
clean
0tells
0 distinct · aes 0 · floor 0
arm=noslop · subject=lighthouse · rep=2 · model=deepseek-v4.1-flash
r2/noslop-lighthouse-3
clean
0tells
0 distinct · aes 0 · floor 0
arm=noslop · subject=lighthouse · rep=3 · model=deepseek-v4.1-flash
r2/noslop-saas-1
clean
0tells
0 distinct · aes 0 · floor 0
arm=noslop · subject=saas · rep=1 · model=deepseek-v4.1-flash
r2/noslop-saas-2
clean
0tells
0 distinct · aes 0 · floor 0
arm=noslop · subject=saas · rep=2 · model=deepseek-v4.1-flash
r2/noslop-saas-3
clean
0tells
0 distinct · aes 0 · floor 0
arm=noslop · subject=saas · rep=3 · model=deepseek-v4.1-flash
r2/rules-hotsauce-1
review
0tells
0 distinct · aes 0 · floor 0
arm=rules · subject=hotsauce · rep=1 · model=deepseek-v4.1-flash
r2/rules-hotsauce-2
no build
--tells
not scanned
arm=rules · subject=hotsauce · rep=2 · model=deepseek-v4.1-flash
no screenshot
r2/rules-hotsauce-3
no build
--tells
not scanned
arm=rules · subject=hotsauce · rep=3 · model=deepseek-v4.1-flash
no screenshot
r2/rules-lighthouse-1
clean
0tells
0 distinct · aes 0 · floor 0
arm=rules · subject=lighthouse · rep=1 · model=deepseek-v4.1-flash
r2/rules-lighthouse-2
review
0tells
0 distinct · aes 0 · floor 0
arm=rules · subject=lighthouse · rep=2 · model=deepseek-v4.1-flash
r2/rules-lighthouse-3
review
2tells
2 distinct · aes 2 · floor 0
arm=rules · subject=lighthouse · rep=3 · model=deepseek-v4.1-flash
hidden_without_js, numbered_steps
r2/rules-saas-1
review
0tells
0 distinct · aes 0 · floor 0
arm=rules · subject=saas · rep=1 · model=deepseek-v4.1-flash
r2/rules-saas-2
review
1tells
1 distinct · aes 1 · floor 0
arm=rules · subject=saas · rep=2 · model=deepseek-v4.1-flash
r2/rules-saas-3
review
1tells
1 distinct · aes 1 · floor 0
arm=rules · subject=saas · rep=3 · model=deepseek-v4.1-flash
r2/script-hotsauce-1
clean
0tells
0 distinct · aes 0 · floor 0
arm=script · subject=hotsauce · rep=1 · model=deepseek-v4.1-flash
r2/script-hotsauce-2
clean
0tells
0 distinct · aes 0 · floor 0
arm=script · subject=hotsauce · rep=2 · model=deepseek-v4.1-flash
r2/script-hotsauce-3
no build
--tells
not scanned
arm=script · subject=hotsauce · rep=3 · model=deepseek-v4.1-flash
no screenshot
r2/script-lighthouse-1
clean
0tells
0 distinct · aes 0 · floor 0
arm=script · subject=lighthouse · rep=1 · model=deepseek-v4.1-flash
r2/script-lighthouse-2
no build
--tells
not scanned
arm=script · subject=lighthouse · rep=2 · model=deepseek-v4.1-flash
no screenshot
r2/script-lighthouse-3
clean
0tells
0 distinct · aes 0 · floor 0
arm=script · subject=lighthouse · rep=3 · model=deepseek-v4.1-flash
r2/script-saas-1
no build
--tells
not scanned
arm=script · subject=saas · rep=1 · model=deepseek-v4.1-flash
no screenshot
r2/script-saas-2
clean
0tells
0 distinct · aes 0 · floor 0
arm=script · subject=saas · rep=2 · model=deepseek-v4.1-flash
r2/script-saas-3
clean
0tells
0 distinct · aes 0 · floor 0
arm=script · subject=saas · rep=3 · model=deepseek-v4.1-flash
