DataLearner logo

MiniMax M2 Benchmark Details

MiniMax M2 currently shows benchmark results led by LiveCodeBench (25 / 126, score 83), IF Bench (12 / 33, score 72.30), MMLU Pro (54 / 133, score 82).

Benchmark Results

MiniMax M2

Benchmark Results

Thinking
Tool usage

General Knowledge

2 evaluations
Benchmark / mode
Score
Rank/total
MMLU Pro
Thinking Mode
82
54 / 133
HLE
Thinking Mode
12.50
149 / 181

Other

1 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Thinking Mode
78
126 / 224

Coding and Software Engineer

2 evaluations
Benchmark / mode
Score
Rank/total
LiveCodeBench
Thinking Mode
83
25 / 126
SWE-bench Verified
Thinking ModeTools
69.40
64 / 114

Math and Reasoning

1 evaluations
Benchmark / mode
Score
Rank/total
AIME2025
Thinking Mode
78
60 / 106

AI Agent - Tool Usage

1 evaluations
Benchmark / mode
Score
Rank/total
Terminal-Bench
Thinking ModeTools
24
29 / 35

Common Sense Reasoning

1 evaluations
Benchmark / mode
Score
Rank/total
SimpleBench
Standard Mode
25
58 / 67

Agent Level Benchmark

2 evaluations
Benchmark / mode
Score
Rank/total
τ²-Bench - Telecom
Thinking ModeTools
87
22 / 35
τ²-Bench
Thinking ModeTools
77.20
19 / 43

Instruction Following

1 evaluations
Benchmark / mode
Score
Rank/total
IF Bench
Thinking Mode
72.30
12 / 33

AI Agent - Information Search

1 evaluations
Benchmark / mode
Score
Rank/total
BrowseComp
Thinking ModeTools
44
47 / 54