GPT-4.1 nano Benchmark Details

GPT-4.1 nano currently shows benchmark results led by MMLU (55 / 124, score 80.10), LiveCodeBench (210 / 250, score 32.60), Creative Writing (90 / 106, score 944).

Benchmark Results

GPT-4.1 nano

Benchmark Results

General Knowledge

2 evaluations

Benchmark / mode

Score

Rank/total

MMLU

Standard Mode

80.10

55 / 124

HLE

Standard Mode

3.80

533 / 563

Other

1 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Standard Mode

50.30

409 / 462

Math and Reasoning

3 evaluations

Benchmark / mode

Score

Rank/total

AIME 2024

Standard Mode

29.40

56 / 62

AIME2025

Standard Mode

194 / 215

FrontierMath

Standard Mode

52 / 60

Coding and Software Engineer

2 evaluations

Benchmark / mode

Score

Rank/total

LiveCodeBench

Standard Mode

32.60

210 / 250

IC SWE-Lancer(Diamond)

Standard Mode

15.30

7 / 8

Writing and Creative Capabilities

1 evaluations

Benchmark / mode

Score

Rank/total

Creative Writing

Standard Mode

944

90 / 106

Agent Level Benchmark

4 evaluations

Benchmark / mode

Score

Rank/total

τ²-Bench - Telecom

Standard ModeTools

17.30

255 / 264

Aider-Polyglot

Standard Mode

8.90

57 / 59

Terminal Bench Hard

Standard ModeTools

3.80

219 / 244

τ³-Banking

Standard ModeTools

3.50

161 / 164

Instruction Following

1 evaluations

Benchmark / mode

Score

Rank/total

IF Bench

Standard Mode

258 / 282

AI Agent - Tool Usage

1 evaluations

Benchmark / mode

Score

Rank/total

Terminal-Bench 2.1

Standard ModeTools

3.70

185 / 192

Multimodal Understanding

1 evaluations

Benchmark / mode

Score

Rank/total

MMMU-Pro

Standard Mode

40.10

220 / 227

Compare with other models