Anthropic: Claude Opus 4.6

Benchmarks gegenereerd uit Aibenchy-testsuites op : 19 feb 2026

Categorie-uitsplitsing

Categorie	Volledig geslaagde tests	Score	Consistentie	Slaagpercentage per poging	Instabiele tests	Redeneerscore	Kosten
Anti-AI Tricks	0/2	1.00	1.62	33.3%	2	10.00	$0.03036
Data parsing and extraction	2/2	10.00	10.00	100.0%	0	9.83	$0.07755
Domain specific	0/3	1.00	10.00	0.0%	0	7.61	$0.60915
Instructions following	2/2	9.50	9.99	100.0%	0	9.50	$0.02231
Puzzle Solving	2/3	7.00	10.00	66.7%	0	9.44	$0.03281

Vergelijk Anthropic: Claude Opus 4.6 met...

#15 · Z.ai

Zonder redenering

Score: 5.42

Consistentie: 10.00

Slaagpercentage per poging: 50.0%

Instabiele tests: 0

Kosten per resultaat: 0.0704

Correcte tests: 6/12

Totale kosten: $0.00423

#17 · MiniMax

Redenering (medium)

Score: 5.08

Consistentie: 6.00

Slaagpercentage per poging: 61.1%

Instabiele tests: 6

Kosten per resultaat: 4.0276

Correcte tests: 5/12

Totale kosten: $0.20138

#14 · Qwen

Zonder redenering

Score: 5.67

Consistentie: 9.99

Slaagpercentage per poging: 50.0%

Instabiele tests: 0

Kosten per resultaat: 0.0997

Correcte tests: 6/12

Totale kosten: $0.00599

Vergelijk Anthropic: Claude Opus 4.6 met...