Duel

Crown held5 Nov 2026, 03:50 UTC8a6c37c4d1…26849e

Reigning model

Holds the crown

domFree/attune-j4

Revision: 4a2651b08cb70332bfe9b86ef9b2efaff1825eb8
Submission key: 12d59031ac1dcdc3

81.7%

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

maginion/king-4

Revision: 71cfb15771bfe3864b4beaa617d880f8b3222df6
Submission key: 73c14479bf0c3a1e

5.4%

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 check5.4% − 81.7% = -76.3 ptsneeds ≥ +3.0 ptsNot met

Verdict derivation

recomputed from 240 unitsCrown held

The ledger

Per-task success rates for both sides and their difference
Task	Reigning	Challenger	Δ
Beat block hammer	60.0%9 / 15	0.0%0 / 15	-60.0 pts
Move stapler pad	80.0%12 / 15	0.0%0 / 15	-80.0 pts
Place bread skillet	73.3%11 / 15	6.7%1 / 15	-66.7 pts
Place burger fries	80.0%12 / 15	0.0%0 / 15	-80.0 pts
Place can basket	93.3%14 / 15	0.0%0 / 15	-93.3 pts
Place cans plasticbox	100.0%15 / 15	0.0%0 / 15	-100.0 pts
Place container plate	100.0%15 / 15	53.3%8 / 15	-46.7 pts
Place dual shoes	46.7%7 / 15	0.0%0 / 15	-46.7 pts
Place empty cup	100.0%15 / 15	20.0%3 / 15	-80.0 pts
Place fan	80.0%12 / 15	0.0%0 / 15	-80.0 pts
Place mouse pad	60.0%9 / 15	0.0%0 / 15	-60.0 pts
Place object basket	86.7%13 / 15	0.0%0 / 15	-86.7 pts
Place object scale	80.0%12 / 15	0.0%0 / 15	-80.0 pts
Place object stand	100.0%15 / 15	6.7%1 / 15	-93.3 pts
Place phone stand	80.0%12 / 15	0.0%0 / 15	-80.0 pts
Place shoe	86.7%13 / 15	0.0%0 / 15	-86.7 pts
Averageneeds ≥ 84.7%	81.7%	5.4%	-76.3 pts

challenger average ≥ reigning average + +3.0 pts

5.4% ≥ 81.7% + +3.0 pts · needs ≥ 84.7%

Not met

The reigning model kept the crown

5.4% vs 81.7% · -76.3 pts

Paired outcomes

which side solved each unit

Won

0

Lost

183

Tied

57

Decided

183

Void

0

The paired record

240 units · 183 decided · 57 tied

Reigning
60.0%9/15
Challenger
0.0%0/15
Reigning
80.0%12/15
Challenger
0.0%0/15
Reigning
73.3%11/15
Challenger
6.7%1/15
Reigning
80.0%12/15
Challenger
0.0%0/15
Reigning
93.3%14/15
Challenger
0.0%0/15
Reigning
100.0%15/15
Challenger
0.0%0/15
Reigning
scene 926330156
Reigning
Pass
Challenger
Fail
Reigning
scene 374025350
Reigning
Pass
Challenger
Fail
Reigning
scene 645142558
Reigning
Pass
Challenger
Fail
Reigning
scene 491857302
Reigning
Pass
Challenger
Fail
Reigning
scene 1708651676
Reigning
Pass
Challenger
Fail
Reigning
scene 1788964138
Reigning
Pass
Challenger
Fail
Reigning
scene 700938958
Reigning
Pass
Challenger
Fail
Reigning
scene 827688028
Reigning
Pass
Challenger
Fail
Reigning
scene 825700196
Reigning
Pass
Challenger
Fail
Reigning
scene 25248559
Reigning
Pass
Challenger
Fail
Reigning
scene 1458357887
Reigning
Pass
Challenger
Fail
Reigning
scene 577165848
Reigning
Pass
Challenger
Fail
Reigning
scene 1764298646
Reigning
Pass
Challenger
Fail
Reigning
scene 289581701
Reigning
Pass
Challenger
Fail
Reigning
scene 1985487254
Reigning
Pass
Challenger
Fail
Reigning
100.0%15/15
Challenger
53.3%8/15
Reigning
46.7%7/15
Challenger
0.0%0/15
Reigning
100.0%15/15
Challenger
20.0%3/15
Reigning
80.0%12/15
Challenger
0.0%0/15
Reigning
60.0%9/15
Challenger
0.0%0/15
Reigning
86.7%13/15
Challenger
0.0%0/15
Reigning
80.0%12/15
Challenger
0.0%0/15
Reigning
100.0%15/15
Challenger
6.7%1/15
Reigning
80.0%12/15
Challenger
0.0%0/15
Reigning
86.7%13/15
Challenger
0.0%0/15

Unit	Scene	Reigning	Challenger	Outcome
		60.0%9/15	0.0%0/15	-60.0 pts
		80.0%12/15	0.0%0/15	-80.0 pts
		73.3%11/15	6.7%1/15	-66.7 pts
		80.0%12/15	0.0%0/15	-80.0 pts
		93.3%14/15	0.0%0/15	-93.3 pts
		100.0%15/15	0.0%0/15	-100.0 pts
	scene 926330156	Pass	Fail	Reigning
	scene 374025350	Pass	Fail	Reigning
	scene 645142558	Pass	Fail	Reigning
	scene 491857302	Pass	Fail	Reigning
	scene 1708651676	Pass	Fail	Reigning
	scene 1788964138	Pass	Fail	Reigning
	scene 700938958	Pass	Fail	Reigning
	scene 827688028	Pass	Fail	Reigning
	scene 825700196	Pass	Fail	Reigning
	scene 25248559	Pass	Fail	Reigning
	scene 1458357887	Pass	Fail	Reigning
	scene 577165848	Pass	Fail	Reigning
	scene 1764298646	Pass	Fail	Reigning
	scene 289581701	Pass	Fail	Reigning
	scene 1985487254	Pass	Fail	Reigning
		100.0%15/15	53.3%8/15	-46.7 pts
		46.7%7/15	0.0%0/15	-46.7 pts
		100.0%15/15	20.0%3/15	-80.0 pts
		80.0%12/15	0.0%0/15	-80.0 pts
		60.0%9/15	0.0%0/15	-60.0 pts
		86.7%13/15	0.0%0/15	-86.7 pts
		80.0%12/15	0.0%0/15	-80.0 pts
		100.0%15/15	6.7%1/15	-93.3 pts
		80.0%12/15	0.0%0/15	-80.0 pts
		86.7%13/15	0.0%0/15	-86.7 pts

Provenance

Record: 8a6c37c4d1f8…a126849e
Kind: Duel
Finished: 5 Nov 2026, 03:50 UTC
Wall time: 2h 08m
Units per side: 15 × 16 tasks = 240
Crown rule: challenger average ≥ reigning average + +3.0 pts
Void units: 0.0%
Duel id: 6ecd0ef2349e…9a64c398
Seed block: 9,436,600
Seed block hash: 0xb0b23edec4…41ec8eaa
Spec version: 3
Benchmark commit: e87619a41914…0a166ccc
Benchmark source: 2358200e9bdd…57aa5a09
Reigning weights: 06092389136a…2ab56c1c
Challenger weights: f6f76bd36f3f…2bbb3a18
Block: 273