MAI-Code-1-Flash Benchmark Details

MAI-Code-1-Flash currently shows benchmark results led by IF Bench (11 / 34, score 75), GPQA Diamond (94 / 255, score 84.60), SWE-bench Verified (58 / 119, score 71.60).

Benchmark Results

MAI-Code-1-Flash

Benchmark Results

Scientific Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

unknown

84.60

94 / 255

Repository Engineering

3 evaluations

Benchmark / mode

Score

Rank/total

SWE-bench Verified

unknown

71.60

58 / 119

SWE-bench Multilingual

unknown

65.50

31 / 33

SWE-Bench Pro - Public

unknown

51.20

47 / 66

Mathematics

2 evaluations

Benchmark / mode

Score

Rank/total

AIME 2026

unknown

92.50

23 / 32

FrontierMath

unknown

6.30

35 / 61

Service Workflows

1 evaluations

Benchmark / mode

Score

Rank/total

τ²-Bench - Telecom

unknown

71.70

23 / 31

Instruction Following

1 evaluations

Benchmark / mode

Score

Rank/total

IF Bench

unknown

11 / 34

Agentic Development

1 evaluations

Benchmark / mode

Score

Rank/total

Terminal Bench 2.0

unknown

54.80

30 / 50

Compare with other models