Gemini 2.0 Pro Experimental Benchmark Details

Gemini 2.0 Pro Experimental currently shows benchmark results led by MATH (4 / 42, score 91.80), MMLU (29 / 124, score 86.50), SimpleQA (16 / 47, score 44.30).

Benchmark Results

Gemini 2.0 Pro Experimental

Benchmark Results

General Knowledge

3 evaluations

Benchmark / mode

Score

Rank/total

MMLU

Standard Mode

86.50

29 / 124

MMLU Pro

Standard Mode

79.10

67 / 176

HLE

Standard Mode

6.20

457 / 563

Math and Reasoning

2 evaluations

Benchmark / mode

Score

Rank/total

MATH

Standard Mode

91.80

4 / 42

AIME 2024

Standard Mode

54 / 62

Other

1 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Standard Mode

64.70

360 / 462

Common Sense

1 evaluations

Benchmark / mode

Score

Rank/total

SimpleQA

Standard Mode

44.30

16 / 47

Coding and Software Engineer

1 evaluations

Benchmark / mode

Score

Rank/total

LiveCodeBench

Standard Mode

34.70

200 / 250

Multimodal Understanding

1 evaluations

Benchmark / mode

Score

Rank/total

MMMU

unknown

72.70

41 / 74

Agent Level Benchmark

1 evaluations

Benchmark / mode

Score

Rank/total

Aider-Polyglot

Standard Mode

35.60

40 / 59

Compare with other models