AI BENCHY
Compare
❤️ Made by XCS

Model Name

MiniMax: MiniMax M2.5

Last updated at : Feb 19, 2026

Metric MiniMax: MiniMax M2.5
Rank#17
CompanyMiniMax
Score 5.08
Consistency 6.00
Cost per result 4.0276
Total Cost $0.20138
Tests Correct 5/12
Attempt pass rate 61.1%
Flaky tests 6
Output Tokens 121,028
Reasoning Tokens 165,110

Category Breakdown

Category Fully passed tests Score Consistency Attempt pass rate Flaky tests Reasoning score Cost
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

Compared models

Compare MiniMax: MiniMax M2.5 against...

#16 · Anthropic

Anthropic: Claude Opus 4.6

Reasoning (medium)

Score: 5.42

Consistency: 8.60

Attempt pass rate: 55.5%

Flaky tests: 2

Cost per result: 12.8695

Tests Correct: 6/12

Total Cost: $0.77217

Compare

#18 · Stepfun

StepFun: Step 3.5 Flash

Reasoning (medium)

Score: 4.92

Consistency: 7.34

Attempt pass rate: 58.3%

Flaky tests: 4

Cost per result: 0.0000

Tests Correct: 5/12

Total Cost: $0.00000

Compare

#15 · Z.ai

Z.ai: GLM 5

No Reasoning

Score: 5.42

Consistency: 10.00

Attempt pass rate: 50.0%

Flaky tests: 0

Cost per result: 0.0704

Tests Correct: 6/12

Total Cost: $0.00423

Compare

Quick Compare

Compare MiniMax: MiniMax M2.5 against...