Duel

Crown taken30 Oct 2026, 01:01 UTC50aee91ed8…e8172e

Reigning model

smol2room/vector_level3_v1

Revision: 19b577795a8be25c769803141f33721740a69208
Submission key: a86cacd7403f6dd3

72.9%

Average over the tasks

Beat block hammer
Move stapler pad
Place bread skillet
Place burger fries
Place can basket
Place cans plasticbox
Place container plate
Place dual shoes
Place empty cup
Place fan
Place mouse pad
Place object basket
Place object scale
Place object stand
Place phone stand
Place shoe

Challenger

Holds the crown

smol2room/vector_level3_v2

Revision: f2c037346239a128b88d20fa363fbb7a0c7f74e0
Submission key: 220605b20d2de8bd

77.5%

Average over the tasks

Beat block hammer
Move stapler pad
Place bread skillet
Place burger fries
Place can basket
Place cans plasticbox
Place container plate
Place dual shoes
Place empty cup
Place fan
Place mouse pad
Place object basket
Place object scale
Place object stand
Place phone stand
Place shoe

Margin check77.5% − 72.9% = +4.6 ptsneeds ≥ +3.0 ptsMet

Verdict derivation

recomputed from 240 unitsCrown taken

The ledger

Per-task success rates for both sides and their difference
Task	Reigning	Challenger	Δ
Beat block hammer	40.0%6 / 15	40.0%6 / 15	0.0 pts
Move stapler pad	60.0%9 / 15	73.3%11 / 15	+13.3 pts
Place bread skillet	60.0%9 / 15	80.0%12 / 15	+20.0 pts
Place burger fries	86.7%13 / 15	73.3%11 / 15	-13.3 pts
Place can basket	86.7%13 / 15	80.0%12 / 15	-6.7 pts
Place cans plasticbox	40.0%6 / 15	46.7%7 / 15	+6.7 pts
Place container plate	100.0%15 / 15	100.0%15 / 15	0.0 pts
Place dual shoes	60.0%9 / 15	80.0%12 / 15	+20.0 pts
Place empty cup	100.0%15 / 15	100.0%15 / 15	0.0 pts
Place fan	66.7%10 / 15	80.0%12 / 15	+13.3 pts
Place mouse pad	73.3%11 / 15	80.0%12 / 15	+6.7 pts
Place object basket	86.7%13 / 15	86.7%13 / 15	0.0 pts
Place object scale	73.3%11 / 15	73.3%11 / 15	0.0 pts
Place object stand	100.0%15 / 15	93.3%14 / 15	-6.7 pts
Place phone stand	40.0%6 / 15	53.3%8 / 15	+13.3 pts
Place shoe	93.3%14 / 15	100.0%15 / 15	+6.7 pts
Averageneeds ≥ 75.9%	72.9%	77.5%	+4.6 pts

challenger average ≥ reigning average + +3.0 pts

77.5% ≥ 72.9% + +3.0 pts · needs ≥ 75.9%

Met

The crown moved to the challenger

77.5% vs 72.9% · +4.6 pts

Paired outcomes

which side solved each unit

Won

23

Lost

12

Tied

205

Decided

35

Void

0

The paired record

240 units · 35 decided · 205 tied

Reigning
40.0%6/15
Challenger
40.0%6/15
Reigning
60.0%9/15
Challenger
73.3%11/15
Tied
scene 1577811069
Reigning
Pass
Challenger
Pass
Reigning
scene 1901715477
Reigning
Pass
Challenger
Fail
Tied
scene 18254893
Reigning
Pass
Challenger
Pass
Reigning
scene 1157760090
Reigning
Pass
Challenger
Fail
Tied
scene 1182368792
Reigning
Pass
Challenger
Pass
Challenger
scene 98339813
Reigning
Fail
Challenger
Pass
Tied
scene 2113454879
Reigning
Pass
Challenger
Pass
Tied
scene 730091839
Reigning
Pass
Challenger
Pass
Challenger
scene 174654405
Reigning
Fail
Challenger
Pass
Tied
scene 463866537
Reigning
Pass
Challenger
Pass
Challenger
scene 1981310110
Reigning
Fail
Challenger
Pass
Tied
scene 1530077552
Reigning
Pass
Challenger
Pass
Tied
scene 1746485448
Reigning
Fail
Challenger
Fail
Challenger
scene 1018769013
Reigning
Fail
Challenger
Pass
Tied
scene 1553421817
Reigning
Fail
Challenger
Fail
Reigning
60.0%9/15
Challenger
80.0%12/15
Reigning
86.7%13/15
Challenger
73.3%11/15
Reigning
86.7%13/15
Challenger
80.0%12/15
Reigning
40.0%6/15
Challenger
46.7%7/15
Reigning
100.0%15/15
Challenger
100.0%15/15
Reigning
60.0%9/15
Challenger
80.0%12/15
Reigning
100.0%15/15
Challenger
100.0%15/15
Reigning
66.7%10/15
Challenger
80.0%12/15
Reigning
73.3%11/15
Challenger
80.0%12/15
Reigning
86.7%13/15
Challenger
86.7%13/15
Reigning
73.3%11/15
Challenger
73.3%11/15
Reigning
100.0%15/15
Challenger
93.3%14/15
Reigning
40.0%6/15
Challenger
53.3%8/15
Reigning
93.3%14/15
Challenger
100.0%15/15

Unit	Scene	Reigning	Challenger	Outcome
		40.0%6/15	40.0%6/15	0.0 pts
		60.0%9/15	73.3%11/15	+13.3 pts
	scene 1577811069	Pass	Pass	Tied
	scene 1901715477	Pass	Fail	Reigning
	scene 18254893	Pass	Pass	Tied
	scene 1157760090	Pass	Fail	Reigning
	scene 1182368792	Pass	Pass	Tied
	scene 98339813	Fail	Pass	Challenger
	scene 2113454879	Pass	Pass	Tied
	scene 730091839	Pass	Pass	Tied
	scene 174654405	Fail	Pass	Challenger
	scene 463866537	Pass	Pass	Tied
	scene 1981310110	Fail	Pass	Challenger
	scene 1530077552	Pass	Pass	Tied
	scene 1746485448	Fail	Fail	Tied
	scene 1018769013	Fail	Pass	Challenger
	scene 1553421817	Fail	Fail	Tied
		60.0%9/15	80.0%12/15	+20.0 pts
		86.7%13/15	73.3%11/15	-13.3 pts
		86.7%13/15	80.0%12/15	-6.7 pts
		40.0%6/15	46.7%7/15	+6.7 pts
		100.0%15/15	100.0%15/15	0.0 pts
		60.0%9/15	80.0%12/15	+20.0 pts
		100.0%15/15	100.0%15/15	0.0 pts
		66.7%10/15	80.0%12/15	+13.3 pts
		73.3%11/15	80.0%12/15	+6.7 pts
		86.7%13/15	86.7%13/15	0.0 pts
		73.3%11/15	73.3%11/15	0.0 pts
		100.0%15/15	93.3%14/15	-6.7 pts
		40.0%6/15	53.3%8/15	+13.3 pts
		93.3%14/15	100.0%15/15	+6.7 pts

Provenance

Record: 50aee91ed879…59e8172e
Kind: Duel
Finished: 30 Oct 2026, 01:01 UTC
Wall time: 1h 29m
Units per side: 15 × 16 tasks = 240
Crown rule: challenger average ≥ reigning average + +3.0 pts
Void units: 0.0%
Duel id: f6c291314986…53b11297
Seed block: 9,392,756
Seed block hash: 0xb6ccb1b037…8dee918a
Spec version: 3
Benchmark commit: e87619a41914…0a166ccc
Benchmark source: 2358200e9bdd…57aa5a09
Reigning weights: de111ca5d135…5c621867
Challenger weights: a434174c05cc…b6b97f1b
Block: 203