AI BENCHY
Linganisha
❤️ Made by XCS

Jina la modeli

MiniMax: MiniMax M2.5

Benchmark zimetengenezwa kutoka seti za majaribio za Aibenchy tarehe : 19 Feb 2026

Kipimo MiniMax: MiniMax M2.5
Nafasi#17
KampuniMiniMax
Score 5.08
Uthabiti 6.00
Gharama kwa matokeo 4.0276
Jumla ya gharama $0.20138
Majaribio sahihi 5/12
Kiwango cha kupita kwa kila jaribio 61.1%
Majaribio yasiyo thabiti 6
Tokeni za matokeo 121,028
Tokeni za hoja 165,110

Mgawanyo wa kategoria

Kategoria Majaribio yaliyopita kikamilifu Score Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Alama ya hoja Gharama
Anti-AI Tricks 2/2 10.00 10.00 100.0% 0 7.58 $0.00902
Data parsing and extraction 1/2 5.50 5.81 83.3% 1 9.45 $0.00774
Domain specific 0/3 1.00 4.41 22.2% 2 6.06 $0.16952
Instructions following 1/2 7.00 6.41 66.7% 1 8.33 $0.00307
Puzzle Solving 1/3 4.33 4.79 55.5% 2 8.28 $0.01205

Modeli zilizolinganishwa

Linganisha MiniMax: MiniMax M2.5 dhidi ya...

#16 · Anthropic

Anthropic: Claude Opus 4.6

Uchambuzi (medium)

Score: 5.42

Uthabiti: 8.60

Kiwango cha kupita kwa kila jaribio: 55.5%

Majaribio yasiyo thabiti: 2

Gharama kwa matokeo: 12.8695

Majaribio sahihi: 6/12

Jumla ya gharama: $0.77217

Linganisha

#18 · Stepfun

StepFun: Step 3.5 Flash

Uchambuzi (medium)

Score: 4.92

Uthabiti: 7.34

Kiwango cha kupita kwa kila jaribio: 58.3%

Majaribio yasiyo thabiti: 4

Gharama kwa matokeo: 0.0000

Majaribio sahihi: 5/12

Jumla ya gharama: $0.00000

Linganisha

#15 · Z.ai

Z.ai: GLM 5

Bila uchambuzi

Score: 5.42

Uthabiti: 10.00

Kiwango cha kupita kwa kila jaribio: 50.0%

Majaribio yasiyo thabiti: 0

Gharama kwa matokeo: 0.0704

Majaribio sahihi: 6/12

Jumla ya gharama: $0.00423

Linganisha

Ulinganisho wa haraka

Linganisha MiniMax: MiniMax M2.5 dhidi ya...