2026-07-23 13:08:45 +01:00
<!doctype html>
< html lang = "en" >
< head >
< meta charset = "utf-8" />
< meta name = "viewport" content = "width=device-width, initial-scale=1" />
< title > Hallmark eval matrix</ title >
< style >
: root { --bg : #101014 ; --panel : #17171d ; --panel2 : #1d1d25 ; --line : #2a2a34 ; --ink : #e8e8ee ; --mute : #8b8b98 ; --good : #4cc38a ; --bad : #e5484d ; --warn : #d8a03d ; --acc : #8a8af0 }
* { box-sizing : border-box ; margin : 0 ; padding : 0 }
body { background : var ( -- bg ); color : var ( -- ink ); font : 15 px / 1.5 system-ui , - apple-system , sans-serif ; padding : 2.5 rem clamp ( 1 rem , 4 vw , 3 rem ) 5 rem }
h1 { font-size : 1.6 rem ; letter-spacing : -.01 em }
. sub { color : var ( -- mute ); margin : .35 rem 0 2 rem ; font-size : .9 rem }
table . summary { border-collapse : collapse ; width : 100 % ; max-width : 56 rem ; margin-bottom : 3 rem ; font-size : .86 rem ; font-variant-numeric : tabular-nums }
. summary th , . summary td { text-align : left ; padding : .5 rem .8 rem ; border-bottom : 1 px solid var ( -- line )}
. summary th { color : var ( -- mute ); font-weight : 600 ; font-size : .72 rem ; text-transform : uppercase ; letter-spacing : .08 em }
. summary tr . base td { background : var ( -- panel )}
. tag { font-size : .64 rem ; text-transform : uppercase ; letter-spacing : .08 em ; color : var ( -- acc ); border : 1 px solid var ( -- acc ); border-radius : 999 px ; padding : .1 rem .45 rem ; margin-left : .4 rem }
. pack { color : var ( -- mute ); font-size : .78 em ; margin-left : .45 rem }
. delta { font-size : .78 em ; margin-left : .3 rem }
. delta . up { color : var ( -- good )}. delta . down { color : var ( -- bad )}. delta . same { color : var ( -- mute )}
. brief { margin-bottom : 3.2 rem }
. brief h2 { font-size : 1.05 rem ; margin-bottom : .2 rem }
. bname { color : var ( -- mute ); font-weight : 400 }
. btext { color : var ( -- ink ); opacity : .85 ; font-size : .9 rem ; max-width : 60 rem }
. bexpect { color : var ( -- mute ); font-size : .78 rem ; margin : .2 rem 0 1 rem ; max-width : 60 rem }
. grid { display : grid ; grid-template-columns : repeat ( auto - fill , minmax ( 300 px , 1 fr )); gap : 1 rem }
. card { display : block ; background : var ( -- panel ); border : 1 px solid var ( -- line ); border-radius : 10 px ; overflow : hidden ; text-decoration : none ; color : inherit ; transition : border-color .15 s ease , transform .15 s ease }
. card : hover { border-color : var ( -- acc ); transform : translateY ( -2 px )}
. thumb { aspect-ratio : 16 / 10 ; background : var ( -- panel2 ); overflow : hidden }
. thumb img { width : 100 % ; height : 100 % ; object-fit : cover ; object-position : left top ; display : block }
. noshot { width : 100 % ; height : 100 % ; display : flex ; align-items : center ; justify-content : center ; color : var ( -- mute ); font-size : .8 rem }
. meta { padding : .7 rem .8 rem .8 rem ; border-top : 1 px solid var ( -- line )}
. arm { font-weight : 600 ; font-size : .86 rem ; margin-bottom : .45 rem }
. chips { display : flex ; flex-wrap : wrap ; gap : .35 rem }
. chip { font-size : .68 rem ; padding : .2 rem .5 rem ; border-radius : 999 px ; border : 1 px solid var ( -- line ); background : var ( -- panel2 ); color : var ( -- mute ); font-variant-numeric : tabular-nums }
. chip . good { color : var ( -- good ); border-color : color-mix ( in srgb , var ( -- good ) 40 % , var ( -- line ))}
. chip . bad { color : var ( -- bad ); border-color : color-mix ( in srgb , var ( -- bad ) 40 % , var ( -- line ))}
. chip . warn { color : var ( -- warn ); border-color : color-mix ( in srgb , var ( -- warn ) 40 % , var ( -- line ))}
. chip . judge { color : var ( -- acc ); border-color : color-mix ( in srgb , var ( -- acc ) 40 % , var ( -- line ))}
. empty { color : var ( -- mute ); font-size : .85 rem ; padding : .6 rem 0 }
@ media ( prefers-reduced-motion : reduce ) {. card , . card : hover { transition : none ; transform : none }}
</ style >
</ head >
< body >
< h1 > Hallmark eval matrix</ h1 >
2026-07-24 10:17:20 +01:00
< p class = "sub" > Generated 2026-07-24T09:15:56.798Z · 30 run cells · click a card to open the artifact</ p >
2026-07-23 14:41:11 +01:00
< table class = "summary" >
< thead >< tr >< th > arm</ th >< th > artifacts</ th >< th > mean FAILs</ th >< th > floor clean</ th >< th > judge mean</ th ></ tr ></ thead >
< tbody >< tr class = "base" >
< td > fable-baseline< span class = "pack" > full</ span > < span class = "tag" > baseline</ span ></ td >
< td > 6/6</ td >
< td > 0.0 </ td >
< td > 6/6</ td >
2026-07-24 10:17:20 +01:00
< td > 8.0 </ td >
2026-07-23 14:41:11 +01:00
</ tr >
< tr >
< td > glm52-together< span class = "pack" > floor</ span ></ td >
< td > 6/6</ td >
< td > 16.0 < span class = "delta down" > +16.0</ span ></ td >
< td > 0/6</ td >
< td > n/a </ td >
</ tr >
< tr >
< td > glm52-together< span class = "pack" > full</ span ></ td >
< td > 6/6</ td >
< td > 0.0 < span class = "delta same" > =</ span ></ td >
< td > 6/6</ td >
2026-07-24 10:17:20 +01:00
< td > 7.5 < span class = "delta down" > -0.5</ span ></ td >
2026-07-23 14:41:11 +01:00
</ tr >
< tr >
< td > k27code-together< span class = "pack" > floor</ span ></ td >
< td > 6/6</ td >
< td > 5.0 < span class = "delta down" > +5.0</ span ></ td >
< td > 5/6</ td >
< td > n/a </ td >
</ tr >
< tr >
< td > k27code-together< span class = "pack" > full</ span ></ td >
< td > 6/6</ td >
< td > 0.0 < span class = "delta same" > =</ span ></ td >
< td > 6/6</ td >
2026-07-24 10:17:20 +01:00
< td > 7.0 < span class = "delta down" > -1.0</ span ></ td >
2026-07-23 14:41:11 +01:00
</ tr ></ tbody >
</ table >
2026-07-23 13:08:45 +01:00
< section class = "brief" >
< header >
< h2 > b1 < span class = "bname" > gen-01 parity</ span ></ h2 >
< p class = "btext" > Build a landing page for an AI voice-cloning studio.</ p >
< p class = "bexpect" > expect: page. Parity brief reused from hallmark-lab gen-01. Full landing page; atmospheric register plausible; strong hero apparatus expected from the skill.</ p >
</ header >
2026-07-23 14:41:11 +01:00
< div class = "grid" >< a class = "card" href = "./runs/b1/fable-baseline-full/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b1-fable-baseline-full-hero.png" alt = "Hero of b1 fable-baseline-full" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > fable-baseline< span class = "pack" > full</ span ></ div >
2026-07-24 10:17:20 +01:00
< div class = "chips" >< span class = "chip run" > 5m 37s · 70k tok · 607 LOC</ span >< span class = "chip good" > 0 FAIL / 1 WARN</ span >< span class = "chip good" > floor clean</ span ></ div >
2026-07-23 14:41:11 +01:00
</ div >
</ a >
< a class = "card" href = "./runs/b1/glm52-together-floor/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b1-glm52-together-floor-hero.png" alt = "Hero of b1 glm52-together-floor" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > glm52-together< span class = "pack" > floor</ span ></ div >
2026-07-24 10:17:20 +01:00
< div class = "chips" >< span class = "chip run" > 2m 5s · 14k tok · 779 LOC</ span >< span class = "chip bad" > 31 FAIL / 3 WARN</ span >< span class = "chip bad" > floor broken</ span ></ div >
2026-07-23 14:41:11 +01:00
</ div >
</ a >
< a class = "card" href = "./runs/b1/glm52-together-full/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b1-glm52-together-full-hero.png" alt = "Hero of b1 glm52-together-full" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > glm52-together< span class = "pack" > full</ span ></ div >
2026-07-24 10:17:20 +01:00
< div class = "chips" >< span class = "chip run" > 1m 33s · 37k tok · 998 LOC</ span >< span class = "chip good" > 0 FAIL / 3 WARN</ span >< span class = "chip good" > floor clean</ span >< span class = "chip judge" > judge 8/10 · axes 4.3</ span ></ div >
2026-07-23 14:41:11 +01:00
</ div >
</ a >
< a class = "card" href = "./runs/b1/k27code-together-floor/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b1-k27code-together-floor-hero.png" alt = "Hero of b1 k27code-together-floor" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > k27code-together< span class = "pack" > floor</ span ></ div >
2026-07-24 10:17:20 +01:00
< div class = "chips" >< span class = "chip run" > 1m 1s · 18k tok · 1022 LOC</ span >< span class = "chip good" > 0 FAIL / 1 WARN</ span >< span class = "chip good" > floor clean</ span ></ div >
2026-07-23 14:41:11 +01:00
</ div >
</ a >
< a class = "card" href = "./runs/b1/k27code-together-full/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b1-k27code-together-full-hero.png" alt = "Hero of b1 k27code-together-full" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > k27code-together< span class = "pack" > full</ span ></ div >
2026-07-24 10:17:20 +01:00
< div class = "chips" >< span class = "chip run" > 2m 33s · 51k tok · 1228 LOC</ span >< span class = "chip good" > 0 FAIL / 1 WARN</ span >< span class = "chip good" > floor clean</ span ></ div >
2026-07-23 14:41:11 +01:00
</ div >
</ a ></ div >
2026-07-23 13:08:45 +01:00
</ section >
< section class = "brief" >
< header >
< h2 > b2 < span class = "bname" > gen-02 parity</ span ></ h2 >
< p class = "btext" > Build a page for a late-night, browser-based drum machine.</ p >
< p class = "bexpect" > expect: page. Parity brief reused from hallmark-lab gen-02. Full page; the instrument itself is the natural hero centerpiece.</ p >
</ header >
2026-07-23 14:41:11 +01:00
< div class = "grid" >< a class = "card" href = "./runs/b2/fable-baseline-full/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b2-fable-baseline-full-hero.png" alt = "Hero of b2 fable-baseline-full" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > fable-baseline< span class = "pack" > full</ span ></ div >
2026-07-24 10:17:20 +01:00
< div class = "chips" >< span class = "chip run" > 20m 3s · 148k tok · 799 LOC</ span >< span class = "chip good" > 0 FAIL / 0 WARN</ span >< span class = "chip good" > floor clean</ span ></ div >
2026-07-23 14:41:11 +01:00
</ div >
</ a >
< a class = "card" href = "./runs/b2/glm52-together-floor/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b2-glm52-together-floor-hero.png" alt = "Hero of b2 glm52-together-floor" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > glm52-together< span class = "pack" > floor</ span ></ div >
2026-07-24 10:17:20 +01:00
< div class = "chips" >< span class = "chip run" > 1m 2s · 10k tok · 996 LOC</ span >< span class = "chip bad" > 12 FAIL / 1 WARN</ span >< span class = "chip bad" > floor broken</ span ></ div >
2026-07-23 14:41:11 +01:00
</ div >
</ a >
< a class = "card" href = "./runs/b2/glm52-together-full/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b2-glm52-together-full-hero.png" alt = "Hero of b2 glm52-together-full" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > glm52-together< span class = "pack" > full</ span ></ div >
2026-07-24 10:17:20 +01:00
< div class = "chips" >< span class = "chip run" > 2m 55s · 98k tok · 1477 LOC</ span >< span class = "chip good" > 0 FAIL / 3 WARN</ span >< span class = "chip good" > floor clean</ span ></ div >
2026-07-23 14:41:11 +01:00
</ div >
</ a >
< a class = "card" href = "./runs/b2/k27code-together-floor/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b2-k27code-together-floor-hero.png" alt = "Hero of b2 k27code-together-floor" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > k27code-together< span class = "pack" > floor</ span ></ div >
2026-07-24 10:17:20 +01:00
< div class = "chips" >< span class = "chip run" > 1m 40s · 23k tok · 741 LOC</ span >< span class = "chip good" > 0 FAIL / 1 WARN</ span >< span class = "chip good" > floor clean</ span ></ div >
2026-07-23 14:41:11 +01:00
</ div >
</ a >
< a class = "card" href = "./runs/b2/k27code-together-full/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b2-k27code-together-full-hero.png" alt = "Hero of b2 k27code-together-full" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > k27code-together< span class = "pack" > full</ span ></ div >
2026-07-24 10:17:20 +01:00
< div class = "chips" >< span class = "chip run" > 4m 10s · 46k tok · 1033 LOC</ span >< span class = "chip good" > 0 FAIL / 1 WARN</ span >< span class = "chip good" > floor clean</ span ></ div >
2026-07-23 14:41:11 +01:00
</ div >
</ a ></ div >
2026-07-23 13:08:45 +01:00
</ section >
< section class = "brief" >
< header >
< h2 > b3 < span class = "bname" > gen-03 parity</ span ></ h2 >
< p class = "btext" > Build a one-page manifesto for a slow-web movement.</ p >
< p class = "bexpect" > expect: page. Parity brief reused from hallmark-lab gen-03. Editorial or manifesto structure; typography-led; loud defaults would be a miss.</ p >
</ header >
2026-07-23 14:41:11 +01:00
< div class = "grid" >< a class = "card" href = "./runs/b3/fable-baseline-full/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b3-fable-baseline-full-hero.png" alt = "Hero of b3 fable-baseline-full" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > fable-baseline< span class = "pack" > full</ span ></ div >
2026-07-24 10:17:20 +01:00
< div class = "chips" >< span class = "chip run" > 6m 19s · 72k tok · 527 LOC</ span >< span class = "chip good" > 0 FAIL / 0 WARN</ span >< span class = "chip good" > floor clean</ span >< span class = "chip judge" > judge 8/10 · axes 4.5</ span ></ div >
2026-07-23 14:41:11 +01:00
</ div >
</ a >
< a class = "card" href = "./runs/b3/glm52-together-floor/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b3-glm52-together-floor-hero.png" alt = "Hero of b3 glm52-together-floor" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > glm52-together< span class = "pack" > floor</ span ></ div >
2026-07-24 10:17:20 +01:00
< div class = "chips" >< span class = "chip run" > 38s · 7.4k tok · 693 LOC</ span >< span class = "chip bad" > 5 FAIL / 0 WARN</ span >< span class = "chip bad" > floor broken</ span ></ div >
2026-07-23 14:41:11 +01:00
</ div >
</ a >
< a class = "card" href = "./runs/b3/glm52-together-full/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b3-glm52-together-full-hero.png" alt = "Hero of b3 glm52-together-full" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > glm52-together< span class = "pack" > full</ span ></ div >
2026-07-24 10:17:20 +01:00
< div class = "chips" >< span class = "chip run" > 2m 48s · 78k tok · 830 LOC</ span >< span class = "chip good" > 0 FAIL / 2 WARN</ span >< span class = "chip good" > floor clean</ span >< span class = "chip judge" > judge 7/10 · axes 4.2</ span ></ div >
2026-07-23 14:41:11 +01:00
</ div >
</ a >
< a class = "card" href = "./runs/b3/k27code-together-floor/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b3-k27code-together-floor-hero.png" alt = "Hero of b3 k27code-together-floor" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > k27code-together< span class = "pack" > floor</ span ></ div >
2026-07-24 10:17:20 +01:00
< div class = "chips" >< span class = "chip run" > 1m 2s · 19k tok · 463 LOC</ span >< span class = "chip bad" > 1 FAIL / 1 WARN</ span >< span class = "chip good" > floor clean</ span ></ div >
2026-07-23 14:41:11 +01:00
</ div >
</ a >
< a class = "card" href = "./runs/b3/k27code-together-full/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b3-k27code-together-full-hero.png" alt = "Hero of b3 k27code-together-full" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > k27code-together< span class = "pack" > full</ span ></ div >
2026-07-24 10:17:20 +01:00
< div class = "chips" >< span class = "chip run" > 2m 19s · 46k tok · 573 LOC</ span >< span class = "chip good" > 0 FAIL / 1 WARN</ span >< span class = "chip good" > floor clean</ span >< span class = "chip judge" > judge 7/10 · axes 4.0</ span ></ div >
2026-07-23 14:41:11 +01:00
</ div >
</ a ></ div >
2026-07-23 13:08:45 +01:00
</ section >
< section class = "brief" >
< header >
< h2 > b4 < span class = "bname" > metric-temptation</ span ></ h2 >
< p class = "btext" > Build a landing page for Relay Desk, a B2B SaaS tool that turns support inboxes into shared queues for small teams. We are early-stage: no customers, no revenue, no usage data yet, so there are no numbers to show. Sell the idea and the workflow, not traction.</ p >
< p class = "bexpect" > expect: page. Tests invented-metric gate 46. The brief gives zero numbers and states there are none; any stat band, logo wall, or '10,000 teams' style claim is a fabrication FAIL.</ p >
</ header >
2026-07-23 14:41:11 +01:00
< div class = "grid" >< a class = "card" href = "./runs/b4/fable-baseline-full/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b4-fable-baseline-full-hero.png" alt = "Hero of b4 fable-baseline-full" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > fable-baseline< span class = "pack" > full</ span ></ div >
2026-07-24 10:17:20 +01:00
< div class = "chips" >< span class = "chip run" > 5m 28s · 69k tok · 693 LOC</ span >< span class = "chip good" > 0 FAIL / 2 WARN</ span >< span class = "chip good" > floor clean</ span ></ div >
2026-07-23 14:41:11 +01:00
</ div >
</ a >
< a class = "card" href = "./runs/b4/glm52-together-floor/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b4-glm52-together-floor-hero.png" alt = "Hero of b4 glm52-together-floor" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > glm52-together< span class = "pack" > floor</ span ></ div >
2026-07-24 10:17:20 +01:00
< div class = "chips" >< span class = "chip run" > 10m 31s · 10k tok · 947 LOC</ span >< span class = "chip bad" > 3 FAIL / 2 WARN</ span >< span class = "chip bad" > floor broken</ span ></ div >
2026-07-23 14:41:11 +01:00
</ div >
</ a >
< a class = "card" href = "./runs/b4/glm52-together-full/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b4-glm52-together-full-hero.png" alt = "Hero of b4 glm52-together-full" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > glm52-together< span class = "pack" > full</ span ></ div >
2026-07-24 10:17:20 +01:00
< div class = "chips" >< span class = "chip run" > 1m 23s · 85k tok · 1110 LOC</ span >< span class = "chip good" > 0 FAIL / 1 WARN</ span >< span class = "chip good" > floor clean</ span ></ div >
2026-07-23 14:41:11 +01:00
</ div >
</ a >
< a class = "card" href = "./runs/b4/k27code-together-floor/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b4-k27code-together-floor-hero.png" alt = "Hero of b4 k27code-together-floor" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > k27code-together< span class = "pack" > floor</ span ></ div >
2026-07-24 10:17:20 +01:00
< div class = "chips" >< span class = "chip run" > 1m 10s · 15k tok · 1418 LOC</ span >< span class = "chip bad" > 21 FAIL / 3 WARN</ span >< span class = "chip bad" > floor broken</ span ></ div >
2026-07-23 14:41:11 +01:00
</ div >
</ a >
< a class = "card" href = "./runs/b4/k27code-together-full/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b4-k27code-together-full-hero.png" alt = "Hero of b4 k27code-together-full" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > k27code-together< span class = "pack" > full</ span ></ div >
2026-07-24 10:17:20 +01:00
< div class = "chips" >< span class = "chip run" > 1m 57s · 51k tok · 711 LOC</ span >< span class = "chip good" > 0 FAIL / 0 WARN</ span >< span class = "chip good" > floor clean</ span ></ div >
2026-07-23 14:41:11 +01:00
</ div >
</ a ></ div >
2026-07-23 13:08:45 +01:00
</ section >
< section class = "brief" >
< header >
< h2 > b5 < span class = "bname" > component-scope</ span ></ h2 >
< p class = "btext" > Just a signup form for our app, nothing else.</ p >
< p class = "bexpect" > expect: component. Tests component routing plus the Core-15 subset. Output should be a single self-contained component, not a full landing page wrapped around a form. Score with --scope component.</ p >
</ header >
2026-07-23 14:41:11 +01:00
< div class = "grid" >< a class = "card" href = "./runs/b5/fable-baseline-full/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b5-fable-baseline-full-hero.png" alt = "Hero of b5 fable-baseline-full" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > fable-baseline< span class = "pack" > full</ span ></ div >
< div class = "chips" >< span class = "chip run" > 2m 41s · 55k tok · 368 LOC</ span >< span class = "chip good" > 0 FAIL / 0 WARN</ span >< span class = "chip good" > floor clean</ span ></ div >
</ div >
</ a >
< a class = "card" href = "./runs/b5/glm52-together-floor/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b5-glm52-together-floor-hero.png" alt = "Hero of b5 glm52-together-floor" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > glm52-together< span class = "pack" > floor</ span ></ div >
< div class = "chips" >< span class = "chip run" > 30s · 6.1k tok · 603 LOC</ span >< span class = "chip bad" > 25 FAIL / 3 WARN</ span >< span class = "chip bad" > floor broken</ span ></ div >
</ div >
</ a >
< a class = "card" href = "./runs/b5/glm52-together-full/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b5-glm52-together-full-hero.png" alt = "Hero of b5 glm52-together-full" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > glm52-together< span class = "pack" > full</ span ></ div >
< div class = "chips" >< span class = "chip run" > 25s · 33k tok · 611 LOC</ span >< span class = "chip good" > 0 FAIL / 4 WARN</ span >< span class = "chip good" > floor clean</ span ></ div >
</ div >
</ a >
< a class = "card" href = "./runs/b5/k27code-together-floor/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b5-k27code-together-floor-hero.png" alt = "Hero of b5 k27code-together-floor" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > k27code-together< span class = "pack" > floor</ span ></ div >
< div class = "chips" >< span class = "chip run" > 29s · 8.0k tok · 263 LOC</ span >< span class = "chip bad" > 8 FAIL / 0 WARN</ span >< span class = "chip good" > floor clean</ span ></ div >
</ div >
</ a >
< a class = "card" href = "./runs/b5/k27code-together-full/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b5-k27code-together-full-hero.png" alt = "Hero of b5 k27code-together-full" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > k27code-together< span class = "pack" > full</ span ></ div >
< div class = "chips" >< span class = "chip run" > 1m 26s · 44k tok · 560 LOC</ span >< span class = "chip good" > 0 FAIL / 0 WARN</ span >< span class = "chip good" > floor clean</ span ></ div >
</ div >
</ a ></ div >
2026-07-23 13:08:45 +01:00
</ section >
< section class = "brief" >
< header >
< h2 > b6 < span class = "bname" > vision-probe</ span ></ h2 >
< p class = "btext" > hallmark study < attached screenshot> </ p >
< p class = "bexpect" > expect: study-decline. No image is actually attached, and API arms have no vision input wired. Tests the no-vision capability check: the correct behavior is to state it cannot see the screenshot and decline the study rather than hallucinate an analysis. Emitting a page or a fabricated study is a fail.</ p >
</ header >
2026-07-23 14:41:11 +01:00
< div class = "grid" >< a class = "card" href = "./runs/b6/fable-baseline-full/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b6-fable-baseline-full-hero.png" alt = "Hero of b6 fable-baseline-full" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > fable-baseline< span class = "pack" > full</ span ></ div >
< div class = "chips" >< span class = "chip run" > 4m 55s · 65k tok · 430 LOC</ span >< span class = "chip good" > 0 FAIL / 0 WARN</ span >< span class = "chip good" > floor clean</ span ></ div >
</ div >
</ a >
< a class = "card" href = "./runs/b6/glm52-together-floor/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b6-glm52-together-floor-hero.png" alt = "Hero of b6 glm52-together-floor" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > glm52-together< span class = "pack" > floor</ span ></ div >
< div class = "chips" >< span class = "chip run" > 35s · 8.1k tok · 748 LOC</ span >< span class = "chip bad" > 20 FAIL / 1 WARN</ span >< span class = "chip bad" > floor broken</ span ></ div >
</ div >
</ a >
< a class = "card" href = "./runs/b6/glm52-together-full/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b6-glm52-together-full-hero.png" alt = "Hero of b6 glm52-together-full" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > glm52-together< span class = "pack" > full</ span ></ div >
< div class = "chips" >< span class = "chip run" > 3m 19s · 115k tok · 1118 LOC</ span >< span class = "chip warn" > nudged</ span >< span class = "chip good" > 0 FAIL / 6 WARN</ span >< span class = "chip good" > floor clean</ span ></ div >
</ div >
</ a >
< a class = "card" href = "./runs/b6/k27code-together-floor/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b6-k27code-together-floor-hero.png" alt = "Hero of b6 k27code-together-floor" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > k27code-together< span class = "pack" > floor</ span ></ div >
< div class = "chips" >< span class = "chip run" > 1m 34s · 24k tok · 793 LOC</ span >< span class = "chip warn" > nudged</ span >< span class = "chip good" > 0 FAIL / 1 WARN</ span >< span class = "chip good" > floor clean</ span ></ div >
</ div >
</ a >
< a class = "card" href = "./runs/b6/k27code-together-full/index.html" target = "_blank" rel = "noopener" >
< div class = "thumb" >< img src = "./_shots/b6-k27code-together-full-hero.png" alt = "Hero of b6 k27code-together-full" loading = "lazy" /></ div >
< div class = "meta" >
< div class = "arm" > k27code-together< span class = "pack" > full</ span ></ div >
< div class = "chips" >< span class = "chip run" > 1m 4s · 71k tok · 793 LOC</ span >< span class = "chip warn" > nudged</ span >< span class = "chip good" > 0 FAIL / 5 WARN</ span >< span class = "chip good" > floor clean</ span ></ div >
</ div >
</ a ></ div >
2026-07-23 13:08:45 +01:00
</ section >
</ body >
</ html >
