Gemini 2.0 Flash Experimental Benchmark Details

Gemini 2.0 Flash Experimental currently shows benchmark results led by MMLU (46 / 124, score 83.40), MMLU Pro (81 / 176, score 76.24), SimpleQA (25 / 47, score 29.90).

Benchmark Results

Gemini 2.0 Flash Experimental

Benchmark Results

General Knowledge

3 evaluations

Benchmark / mode

Score

Rank/total

MMLU

Standard Mode

83.40

46 / 124

MMLU Pro

Standard Mode

76.24

81 / 176

HLE

Standard Mode

5.10

478 / 563

Other

1 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Standard Mode

65.20

355 / 462

Common Sense

1 evaluations

Benchmark / mode

Score

Rank/total

SimpleQA

Standard Mode

29.90

25 / 47

Coding and Software Engineer

2 evaluations

Benchmark / mode

Score

Rank/total

LiveCodeBench

Standard Mode

29.10

222 / 250

SWE-bench Verified

Standard Mode

21.40

116 / 116

Math and Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

AIME2025

Standard Mode

29.70

184 / 215

Common Sense Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

SimpleBench

Standard Mode

18.90

89 / 93

Agent Level Benchmark

2 evaluations

Benchmark / mode

Score

Rank/total

Aider-Polyglot

Standard Mode

22.20

47 / 59

Aider-Polyglot

Thinking Enabled

18.20

50 / 59

Compare with other models