Vector-Bench · a thetalab benchmark

theta labs / task

sv_013very_hard

scenic_very_hard

instructionnatural language

The main sail is facing the wrong way, the red buoy stripe has turned green, and the cabin window has slipped out of place. Remove the stray rope by the pier and tidy the rope coil, without changing anything else in the harbor.

initial · brokeninput

target · expected fixcanonical

published model outputs

What each model produced.

34 endpoints

model result explorerClaude Sonnet 5

Claude Sonnet 5

anthropic/claude-sonnet-5

TracePARTIAL

requested repairs

5/6

semantic preservation

clean

SVG validity

valid

source fidelity

unchanged

target match

different

Full pass requires the first three gates. Source fidelity and canonical target match are diagnostics only.

outcome

partial

progress

73.6%

UCR

0.0%

preserve

100.0%

elapsed

1586.0s

cost

$0.0486

requested repairs5/6

rope-coil.dmissed

expected M48 82 C58 72 70 74 70 84 C70 94 54 96 50 88 C46 80 60 78 62 86 / produced M50 86 C60 74 72 78 70 88 C68 98 54 96 56 86 C58 78 66 80 64 86

path-shape: 4.004 <= 1.793 sampled geometry / 0.0% repaired

stray-pier-rope.existspassed

expected false / produced false

required presence matches

cabin-window.xpassed

expected 114 / produced 116

numeric-delta: 2 <= 4 user units / 75.0% repaired

cabin-window.ypassed

expected 67 / produced 68

numeric-delta: 1 <= 1.5 user units / 66.7% repaired

buoy-red-stripe.fillpassed

expected #ef4444 / produced #ef4444

color-lab: 0 <= 18 Delta E76 / 100.0% repaired

sail-main.pointspassed

expected [[126,30],[154,76],[126,76]] / produced [[126,30],[154,76],[126,76]]

points-rms: 0 <= 4.2 coordinate RMS / 100.0% repaired

Why it did not pass

requested repairs incomplete

Unexpected changes

None

Semantic preservation failures

None

Source fidelity diagnostics

None

prompt 3,639 tokoutput 4,132 tokreasoning 0 tokceiling 4,168 tokfinish stopfrontier

resolved anthropic/claude-sonnet-5

response gen-1784564074-1IOfQroAyBOtAYnyZk8a

expected diff6 edits

Part	Attr	Before	After
rope-coil	d	M48 84 C62 70 74 80 68 90 C60 102 44 92 54 82 C62 74 66 86 60 90	M48 82 C58 72 70 74 70 84 C70 94 54 96 50 88 C46 80 60 78 62 86
stray-pier-rope	exists	true	false
cabin-window	x	106	114
cabin-window	y	70	67
buoy-red-stripe	fill	#22c55e	#ef4444
sail-main	points	[[144.66666666666669,30],[116.66666666666669,76],[144.66666666666669,76]]	[[126,30],[154,76],[126,76]]

partsscope

Target (5)

rope-coil

stray-pier-rope

cabin-window

buoy-red-stripe

sail-main

Should preserve (58)

sky

water

horizon

sun

cloud-left

cloud-right

pier-deck

pier-leg-1

pier-leg-2

boat-hull

boat-cabin

mast

sail-small

flag

lighthouse-body

lighthouse-stripe-1

lighthouse-stripe-2

lighthouse-cap

lighthouse-window

light-beam

buoy-red

buoy-green

buoy-green-stripe

wave-1

harbor-wave-long

wave-2

crate-left

crate-right

skin-13-anchor-wide-ring

skin-13-anchor-wide-stem

skin-13-anchor-wide-bar

skin-13-anchor-wide-hook

identity-13-anchor-ring

identity-13-anchor-stem

identity-13-anchor-bar

identity-13-anchor-hook

variant-13-dot

variant-13-rule

variant-13-chip-01

variant-13-chip-02

variant-13-chip-03

variant-13-chip-04

variant-13-chip-05

variant-13-chip-06

variant-13-chip-07

variant-13-chip-08

variant-13-chip-09

variant-13-chip-10

variant-13-chip-11

variant-13-chip-12

variant-13-pin-01

variant-13-pin-02

variant-13-pin-03

variant-13-pin-04

variant-13-pin-05

variant-13-pin-06

variant-13-pin-07

variant-13-pin-08

initial svgsource

<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 220 140" width="220" height="140">
<rect id="__bg" x="0" y="0" width="220" height="140" fill="#fbfff4" />
  <rect id="sky" fill="#e0f2fe" x="0" y="0" width="220" height="70" />
  <rect id="water" fill="#0284c7" x="0" y="70" width="220" height="70" />
  <line id="horizon" stroke="#0284c7" stroke-width="2" x1="0" y1="70" x2="220" y2="70" />
  <circle id="sun" fill="#fde047" cx="190" cy="22" r="12" />
  <ellipse id="cloud-left" fill="#ffffff" cx="36" cy="26" rx="18" ry="7" />
  <ellipse id="cloud-right" fill="#ffffff" cx="56" cy="25" rx="14" ry="6" />
  <rect id="pier-deck" fill="#92400e" x="0" y="88" width="72" height="10" />
  <path id="rope-coil" fill="none" stroke="#f8fafc" stroke-width="2" d="M48 84 C62 70 74 80 68 90 C60 102 44 92 54 82 C62 74 66 86 60 90" />
  <line id="pier-leg-1" stroke="#451a03" stroke-width="4" x1="16" y1="96" x2="13" y2="132" />
  <line id="pier-leg-2" stroke="#451a03" stroke-width="4" x1="56" y1="96" x2="60" y2="132" />
  <polygon id="boat-hull" fill="#92400e" stroke="#222" stroke-width="1" points="84,84 158,84 146,104 96,104" />
  <rect id="boat-cabin" fill="#fef3c7" stroke="#222" stroke-width="1" x="106" y="62" width="30" height="20" />
  <rect id="cabin-window" fill="#93c5fd" stroke="#222" stroke-width="0.8" x="106" y="70" width="14" height="8" />
  <line id="mast" stroke="#222" stroke-width="3" x1="126" y1="84" x2="126" y2="26" />
  <polygon id="sail-main" fill="#f8fafc" stroke="#222" stroke-width="1" points="144.66666666666669,30 116.66666666666669,76 144.66666666666669,76" />
  <polygon id="sail-small" fill="#e0f2fe" stroke="#222" stroke-width="1" points="124,34 100,76 124,76" />
  <polygon id="flag" fill="#84cc16" points="126,25 140,29 126,33" />
  <polygon id="lighthouse-body" fill="#fee2e2" stroke="#222" stroke-width="1" points="176,82 206,82 200,28 182,28" />
  <rect id="lighthouse-stripe-1" fill="#ef4444" x="181" y="48" width="20" height="7" />
  <rect id="lighthouse-stripe-2" fill="#ef4444" x="179" y="64" width="24" height="7" />
  <rect id="lighthouse-cap" fill="#0f172a" x="180" y="22" width="22" height="8" />
  <rect id="lighthouse-window" fill="#fde047" stroke="#222" stroke-width="0.7" x="188" y="34" width="6" height="8" />
  <polygon id="light-beam" fill="#fde68a" opacity="0.45" points="180,30 132,18 132,42" />
  <circle id="buoy-red" fill="#f8fafc" stroke="#222" stroke-width="1" cx="42" cy="112" r="8" />
  <rect id="buoy-red-stripe" fill="#22c55e" x="35" y="110" width="14" height="4" />
  <circle id="buoy-green" fill="#f8fafc" stroke="#222" stroke-width="1" cx="184" cy="112" r="7" />
  <rect id="buoy-green-stripe" fill="#22c55e" x="178" y="110" width="12" height="4" />
  <polyline id="wave-1" fill="none" stroke="#0ea5e9" stroke-width="2" points="6,122 22,118 38,122 54,118 70,122" />
  <path id="harbor-wave-long" fill="none" stroke="#0ea5e9" stroke-width="2" d="M82 118 C98 112 112 124 128 118 S158 112 174 118" />
  <polyline id="wave-2" fill="none" stroke="#0ea5e9" stroke-width="2" points="128,120 146,116 164,120 182,116 200,120" />
  <rect id="crate-left" fill="#a16207" stroke="#451a03" stroke-width="1" x="12" y="76" width="14" height="12" />
  <rect id="crate-right" fill="#b45309" stroke="#451a03" stroke-width="1" x="28" y="76" width="14" height="12" />
  <circle id="skin-13-anchor-wide-ring" fill="none" stroke="#334155" stroke-width="5" opacity="0.9" cx="28" cy="40" r="14" />
  <line id="skin-13-anchor-wide-stem" stroke="#334155" stroke-width="7" opacity="0.9" x1="28" y1="54" x2="28" y2="116" />
  <line id="skin-13-anchor-wide-bar" stroke="#334155" stroke-width="5" opacity="0.9" x1="7" y1="75" x2="50" y2="75" />
  <path id="skin-13-anchor-wide-hook" fill="none" stroke="#334155" stroke-width="7" opacity="0.9" d="M0 104 C18 136 52 136 66 104" />
  <circle id="identity-13-anchor-ring" fill="none" stroke="#334155" stroke-width="3" cx="28" cy="35" r="8" />
  <line id="identity-13-anchor-stem" stroke="#334155" stroke-width="4" x1="28" y1="43" x2="28" y2="86" />
  <line id="identity-13-anchor-bar" stroke="#334155" stroke-width="3" x1="15" y1="58" x2="41" y2="58" />
  <path id="identity-13-anchor-hook" fill="none" stroke="#334155" stroke-width="4" d="M8 76 C16 96 40 96 48 76" />
  <circle id="variant-13-dot" fill="#84cc16" opacity="0.72" cx="39" cy="13" r="2.6" />
  <line id="variant-13-rule" stroke="#84cc16" stroke-width="1.2" opacity="0.58" x1="45" y1="16" x2="61" y2="14" />
  <rect id="variant-13-chip-01" fill="#f97316" opacity="0.68" x="9" y="5" width="8" height="3" rx="1" />
  <rect id="variant-13-chip-02" fill="#f59e0b" opacity="0.68" x="46" y="6" width="9" height="4" rx="1" />
  <rect id="variant-13-chip-03" fill="#84cc16" opacity="0.68" x="77" y="4" width="7" height="3" rx="1" />
  <rect id="variant-13-chip-04" fill="#22c55e" opacity="0.68" x="114" y="5" width="8" height="4" rx="1" />
  <rect id="variant-13-chip-05" fill="#14b8a6" opacity="0.68" x="145" y="6" width="9" height="3" rx="1" />
  <rect id="variant-13-chip-06" fill="#06b6d4" opacity="0.68" x="182" y="4" width="7" height="4" rx="1" />
  <rect id="variant-13-chip-07" fill="#3b82f6" opacity="0.68" x="9" y="140" width="8" height="3" rx="1" />
  <rect id="variant-13-chip-08" fill="#6366f1" opacity="0.68" x="46" y="139" width="9" height="4" rx="1" />
  <rect id="variant-13-chip-09" fill="#8b5cf6" opacity="0.68" x="77" y="141" width="7" height="3" rx="1" />
  <rect id="variant-13-chip-10" fill="#d946ef" opacity="0.68" x="114" y="140" width="8" height="4" rx="1" />
  <rect id="variant-13-chip-11" fill="#ec4899" opacity="0.68" x="145" y="139" width="9" height="3" rx="1" />
  <rect id="variant-13-chip-12" fill="#ef4444" opacity="0.68" x="182" y="141" width="7" height="4" rx="1" />
  <circle id="variant-13-pin-01" fill="#f59e0b" opacity="0.66" cx="27" cy="25" r="2.05" />
  <circle id="variant-13-pin-02" fill="#84cc16" opacity="0.66" cx="212" cy="39" r="2.3" />
  <circle id="variant-13-pin-03" fill="#22c55e" opacity="0.66" cx="13" cy="53" r="2.55" />
  <circle id="variant-13-pin-04" fill="#14b8a6" opacity="0.66" cx="198" cy="67" r="1.8" />
  <circle id="variant-13-pin-05" fill="#06b6d4" opacity="0.66" cx="23" cy="81" r="2.05" />
  <circle id="variant-13-pin-06" fill="#3b82f6" opacity="0.66" cx="208" cy="95" r="2.3" />
  <circle id="variant-13-pin-07" fill="#6366f1" opacity="0.66" cx="9" cy="109" r="2.55" />
  <circle id="variant-13-pin-08" fill="#8b5cf6" opacity="0.66" cx="194" cy="123" r="1.8" />
  <polyline id="stray-pier-rope" fill="none" stroke="#f8fafc" stroke-width="2" points="8,84 20,80 32,84" />
</svg>

target svgsource

<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 220 140" width="220" height="140">
<rect id="__bg" x="0" y="0" width="220" height="140" fill="#fbfff4" />
  <rect id="sky" fill="#e0f2fe" x="0" y="0" width="220" height="70" />
  <rect id="water" fill="#0284c7" x="0" y="70" width="220" height="70" />
  <line id="horizon" stroke="#0284c7" stroke-width="2" x1="0" y1="70" x2="220" y2="70" />
  <circle id="sun" fill="#fde047" cx="190" cy="22" r="12" />
  <ellipse id="cloud-left" fill="#ffffff" cx="36" cy="26" rx="18" ry="7" />
  <ellipse id="cloud-right" fill="#ffffff" cx="56" cy="25" rx="14" ry="6" />
  <rect id="pier-deck" fill="#92400e" x="0" y="88" width="72" height="10" />
  <path id="rope-coil" fill="none" stroke="#f8fafc" stroke-width="2" d="M48 82 C58 72 70 74 70 84 C70 94 54 96 50 88 C46 80 60 78 62 86" />
  <line id="pier-leg-1" stroke="#451a03" stroke-width="4" x1="16" y1="96" x2="13" y2="132" />
  <line id="pier-leg-2" stroke="#451a03" stroke-width="4" x1="56" y1="96" x2="60" y2="132" />
  <polygon id="boat-hull" fill="#92400e" stroke="#222" stroke-width="1" points="84,84 158,84 146,104 96,104" />
  <rect id="boat-cabin" fill="#fef3c7" stroke="#222" stroke-width="1" x="106" y="62" width="30" height="20" />
  <rect id="cabin-window" fill="#93c5fd" stroke="#222" stroke-width="0.8" x="114" y="67" width="14" height="8" />
  <line id="mast" stroke="#222" stroke-width="3" x1="126" y1="84" x2="126" y2="26" />
  <polygon id="sail-main" fill="#f8fafc" stroke="#222" stroke-width="1" points="126,30 154,76 126,76" />
  <polygon id="sail-small" fill="#e0f2fe" stroke="#222" stroke-width="1" points="124,34 100,76 124,76" />
  <polygon id="flag" fill="#84cc16" points="126,25 140,29 126,33" />
  <polygon id="lighthouse-body" fill="#fee2e2" stroke="#222" stroke-width="1" points="176,82 206,82 200,28 182,28" />
  <rect id="lighthouse-stripe-1" fill="#ef4444" x="181" y="48" width="20" height="7" />
  <rect id="lighthouse-stripe-2" fill="#ef4444" x="179" y="64" width="24" height="7" />
  <rect id="lighthouse-cap" fill="#0f172a" x="180" y="22" width="22" height="8" />
  <rect id="lighthouse-window" fill="#fde047" stroke="#222" stroke-width="0.7" x="188" y="34" width="6" height="8" />
  <polygon id="light-beam" fill="#fde68a" opacity="0.45" points="180,30 132,18 132,42" />
  <circle id="buoy-red" fill="#f8fafc" stroke="#222" stroke-width="1" cx="42" cy="112" r="8" />
  <rect id="buoy-red-stripe" fill="#ef4444" x="35" y="110" width="14" height="4" />
  <circle id="buoy-green" fill="#f8fafc" stroke="#222" stroke-width="1" cx="184" cy="112" r="7" />
  <rect id="buoy-green-stripe" fill="#22c55e" x="178" y="110" width="12" height="4" />
  <polyline id="wave-1" fill="none" stroke="#0ea5e9" stroke-width="2" points="6,122 22,118 38,122 54,118 70,122" />
  <path id="harbor-wave-long" fill="none" stroke="#0ea5e9" stroke-width="2" d="M82 118 C98 112 112 124 128 118 S158 112 174 118" />
  <polyline id="wave-2" fill="none" stroke="#0ea5e9" stroke-width="2" points="128,120 146,116 164,120 182,116 200,120" />
  <rect id="crate-left" fill="#a16207" stroke="#451a03" stroke-width="1" x="12" y="76" width="14" height="12" />
  <rect id="crate-right" fill="#b45309" stroke="#451a03" stroke-width="1" x="28" y="76" width="14" height="12" />
  <circle id="skin-13-anchor-wide-ring" fill="none" stroke="#334155" stroke-width="5" opacity="0.9" cx="28" cy="40" r="14" />
  <line id="skin-13-anchor-wide-stem" stroke="#334155" stroke-width="7" opacity="0.9" x1="28" y1="54" x2="28" y2="116" />
  <line id="skin-13-anchor-wide-bar" stroke="#334155" stroke-width="5" opacity="0.9" x1="7" y1="75" x2="50" y2="75" />
  <path id="skin-13-anchor-wide-hook" fill="none" stroke="#334155" stroke-width="7" opacity="0.9" d="M0 104 C18 136 52 136 66 104" />
  <circle id="identity-13-anchor-ring" fill="none" stroke="#334155" stroke-width="3" cx="28" cy="35" r="8" />
  <line id="identity-13-anchor-stem" stroke="#334155" stroke-width="4" x1="28" y1="43" x2="28" y2="86" />
  <line id="identity-13-anchor-bar" stroke="#334155" stroke-width="3" x1="15" y1="58" x2="41" y2="58" />
  <path id="identity-13-anchor-hook" fill="none" stroke="#334155" stroke-width="4" d="M8 76 C16 96 40 96 48 76" />
  <circle id="variant-13-dot" fill="#84cc16" opacity="0.72" cx="39" cy="13" r="2.6" />
  <line id="variant-13-rule" stroke="#84cc16" stroke-width="1.2" opacity="0.58" x1="45" y1="16" x2="61" y2="14" />
  <rect id="variant-13-chip-01" fill="#f97316" opacity="0.68" x="9" y="5" width="8" height="3" rx="1" />
  <rect id="variant-13-chip-02" fill="#f59e0b" opacity="0.68" x="46" y="6" width="9" height="4" rx="1" />
  <rect id="variant-13-chip-03" fill="#84cc16" opacity="0.68" x="77" y="4" width="7" height="3" rx="1" />
  <rect id="variant-13-chip-04" fill="#22c55e" opacity="0.68" x="114" y="5" width="8" height="4" rx="1" />
  <rect id="variant-13-chip-05" fill="#14b8a6" opacity="0.68" x="145" y="6" width="9" height="3" rx="1" />
  <rect id="variant-13-chip-06" fill="#06b6d4" opacity="0.68" x="182" y="4" width="7" height="4" rx="1" />
  <rect id="variant-13-chip-07" fill="#3b82f6" opacity="0.68" x="9" y="140" width="8" height="3" rx="1" />
  <rect id="variant-13-chip-08" fill="#6366f1" opacity="0.68" x="46" y="139" width="9" height="4" rx="1" />
  <rect id="variant-13-chip-09" fill="#8b5cf6" opacity="0.68" x="77" y="141" width="7" height="3" rx="1" />
  <rect id="variant-13-chip-10" fill="#d946ef" opacity="0.68" x="114" y="140" width="8" height="4" rx="1" />
  <rect id="variant-13-chip-11" fill="#ec4899" opacity="0.68" x="145" y="139" width="9" height="3" rx="1" />
  <rect id="variant-13-chip-12" fill="#ef4444" opacity="0.68" x="182" y="141" width="7" height="4" rx="1" />
  <circle id="variant-13-pin-01" fill="#f59e0b" opacity="0.66" cx="27" cy="25" r="2.05" />
  <circle id="variant-13-pin-02" fill="#84cc16" opacity="0.66" cx="212" cy="39" r="2.3" />
  <circle id="variant-13-pin-03" fill="#22c55e" opacity="0.66" cx="13" cy="53" r="2.55" />
  <circle id="variant-13-pin-04" fill="#14b8a6" opacity="0.66" cx="198" cy="67" r="1.8" />
  <circle id="variant-13-pin-05" fill="#06b6d4" opacity="0.66" cx="23" cy="81" r="2.05" />
  <circle id="variant-13-pin-06" fill="#3b82f6" opacity="0.66" cx="208" cy="95" r="2.3" />
  <circle id="variant-13-pin-07" fill="#6366f1" opacity="0.66" cx="9" cy="109" r="2.55" />
  <circle id="variant-13-pin-08" fill="#8b5cf6" opacity="0.66" cx="194" cy="123" r="1.8" />
</svg>