MiniMax M3.1 Flash Benchmark Details

MiniMax M3.1 Flash currently shows benchmark results led by AutomationBench (1 / 46, score 62.80), DeepSWE (10 / 106, score 73.70), CritPt (36 / 208, score 22.29).

Benchmark Results

MiniMax M3.1 Flash

Benchmark Results

Knowledge Exams

2 evaluations

Benchmark / mode

Score

Rank/total

HLE

unknown

47.96

55 / 244

HLE

unknown

43.40

2 / 5

Long Reasoning

2 evaluations

Benchmark / mode

Score

Rank/total

AA-LCR

unknown

79.67

4 / 11

LOCA-Bench 256K

unknownTools

60.30

1 / 1

Repository Engineering

4 evaluations

Benchmark / mode

Score

Rank/total

DeepSWE

HighTools

68.10

35 / 106

DeepSWE

MaxTools

73.70

10 / 106

DeepSWE

Extra-HighTools

72.10

19 / 106

NL2Repo-Bench

unknownTools

61.20

6 / 20

Desktop Workflows

1 evaluations

Benchmark / mode

Score

Rank/total

OSWorld 2.0

unknownTools

61.70

10 / 16

Tool Orchestration

2 evaluations

Benchmark / mode

Score

Rank/total

AutomationBench-AA

unknown

72.52

1 / 5

Agents' Last Exam

MaxTools

29.61

10 / 21

ML Engineering

1 evaluations

Benchmark / mode

Score

Rank/total

PostTrain Bench

unknownTools

39.30

2 / 6

Cross-industry Work

1 evaluations

Benchmark / mode

Score

Rank/total

GDPval-AA v2

unknown

1457.69

6 / 11

Office & Business

9 evaluations

Benchmark / mode

Score

Rank/total

AA-Briefcase

unknown

1651.76

12 / 13

AA-Briefcase

unknown

1473.90

12 / 13

AA-Briefcase

unknown

1425.44

12 / 13

AA-Briefcase

unknown

47.80

12 / 13

AutomationBench

LowTools

52.80

8 / 46

AutomationBench

MediumTools

57.70

5 / 46

AutomationBench

HighTools

59.20

4 / 46

AutomationBench

MaxTools

62.80

1 / 46

AutomationBench

Extra-HighTools

61.20

2 / 46

Visual Understanding

2 evaluations

Benchmark / mode

Score

Rank/total

BabyVision

unknownTools

4 / 13

MMMU-Pro

unknown

79.13

52 / 233

Documents & Charts

2 evaluations

Benchmark / mode

Score

Rank/total

CharXiv RQ

unknownTools

82.50

19 / 25

GDP.pdf

unknown

20.80

39 / 126

Scientific Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

CritPt

unknown

22.29

36 / 208

Scientific Computing

1 evaluations

Benchmark / mode

Score

Rank/total

SciCode

unknown

53.36

56 / 137

Vulnerability Analysis

1 evaluations

Benchmark / mode

Score

Rank/total

CyberGym

unknownTools

82.20

8 / 14

Preference Arenas

1 evaluations

Benchmark / mode

Score

Rank/total

Code Arena WebDev

unknown

1588

1 / 2

Agentic Development

2 evaluations

Benchmark / mode

Score

Rank/total

Terminal-Bench 4.0

unknown

25.76

40 / 108

Terminal-Bench 4.0

unknownTools

38.10

27 / 108

Capability Indices

2 evaluations

Benchmark / mode

Score

Rank/total

AA Intelligence Index v4.3

unknown

42.38

53 / 197

AA Intelligence Index v4.3

Thinking EnabledTools

42.71

51 / 197

Honesty & Factuality

3 evaluations

Benchmark / mode

Score

Rank/total

AA-Omniscience

unknown

92.81

10 / 10

AA-Omniscience

unknown

56.20

10 / 10

AA-Omniscience

unknown

15.55

10 / 10

Finance

1 evaluations

Benchmark / mode

Score

Rank/total

BankerToolBench

unknownTools

76.20

1 / 1

Maintenance & Optimization

1 evaluations

Benchmark / mode

Score

Rank/total

SWE Refactor Bench

unknownTools

1 / 1

Cross-capability Suites

1 evaluations

Benchmark / mode

Score

Rank/total

LiveBench 2.0

MaxTools

73.09

21 / 49

Compare with other models