GPT-4.1 mini Benchmark Details

GPT-4.1 mini currently shows benchmark results led by MMLU (23 / 124, score 87.50), IC SWE-Lancer (Diamond) (4 / 8, score 33), FrontierMath (39 / 60, score 4.50).

Benchmark Results

GPT-4.1 mini

Benchmark Results

Knowledge Exams

1 evaluations

Benchmark / mode

Score

Rank/total

MMLU

Standard Mode

87.50

23 / 124

Scientific Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Standard Mode

200 / 253

Repository Engineering

2 evaluations

Benchmark / mode

Score

Rank/total

IC SWE-Lancer (Diamond)

Standard Mode

4 / 8

SWE-bench Verified

Standard Mode

23.60

114 / 116

Mathematics

2 evaluations

Benchmark / mode

Score

Rank/total

AIME 2024

Standard Mode

49.60

48 / 61

FrontierMath

Standard Mode

4.50

39 / 60

Writing

1 evaluations

Benchmark / mode

Score

Rank/total

Creative Writing

Standard Mode

1147

85 / 110

Agentic Development

2 evaluations

Benchmark / mode

Score

Rank/total

Aider-Polyglot

Standard Mode

32.40

43 / 59

Terminal Bench Hard

Standard ModeTools

7.60

190 / 244

Service Workflows

3 evaluations

Benchmark / mode

Score

Rank/total

τ²-Bench

Standard ModeTools

34 / 44

τ²-Bench - Telecom

Thinking EnabledTools

48.90

29 / 30

τ³-Banking

Standard ModeTools

5.40

152 / 167

Visual Understanding

1 evaluations

Benchmark / mode

Score

Rank/total

MMMU-Pro

Standard Mode

58.70

180 / 229

Capability Indices

1 evaluations

Benchmark / mode

Score

Rank/total

ECI

unknown

135

110 / 167

Compare with other models