Gemini 2.5 Flash Benchmark Details

Gemini 2.5 Flash currently shows benchmark results led by AIME 2024 (16 / 62, score 88), GPQA Diamond (196 / 463, score 82.80), GeoBench ACW (9 / 20, score 76).

Benchmark Results

Gemini 2.5 Flash

Benchmark Results

General Knowledge

9 evaluations

Benchmark / mode

Score

Rank/total

LiveBench

Thinking Level · High

47.74

103 / 117

ARC-AGI-1

Standard Mode

32.30

125 / 147

HLE

Standard Mode

8.40

415 / 565

HLE

Standard Mode

4.70

492 / 565

HLE

unknown

12.08

369 / 565

HLE

Thinking Enabled

12.10

367 / 565

HLE

Thinking Enabled

379 / 565

CritPt

Standard Mode

1.40

136 / 201

CritPt

Thinking Enabled

1.10

148 / 201

Other

2 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Standard Mode

78.30

255 / 463

GPQA Diamond

Thinking Enabled

82.80

196 / 463

Common Sense

2 evaluations

Benchmark / mode

Score

Rank/total

SimpleQA

Standard Mode

25.80

30 / 47

SimpleQA

Thinking Enabled

26.90

29 / 47

Coding and Software Engineer

5 evaluations

Benchmark / mode

Score

Rank/total

LiveCodeBench

Standard Mode

41.10

183 / 251

LiveCodeBench

Thinking Enabled

55.40

151 / 251

SWE-bench Verified

Standard Mode

96 / 116

SWE-bench Verified

Thinking Enabled

48.90

100 / 116

WeirdML v2

16KTools

40.95

46 / 52

Math and Reasoning

5 evaluations

Benchmark / mode

Score

Rank/total

AIME 2024

Standard Mode

16 / 62

AIME2025

Standard Mode

61.60

137 / 216

AIME2025

Thinking Enabled

117 / 216

IMO 2024

Standard Mode

7.80

6 / 10

FrontierMath - Tier 4

Standard Mode

4.20

40 / 80

Writing and Creative Capabilities

1 evaluations

Benchmark / mode

Score

Rank/total

Creative Writing

Standard Mode

1134.60

84 / 106

Common Sense Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

SimpleBench

Standard Mode

41.20

64 / 93

Agent Level Benchmark

7 evaluations

Benchmark / mode

Score

Rank/total

Aider-Polyglot

Standard Mode

47.10

35 / 59

Aider-Polyglot

16K

55.10

27 / 59

BALROG

Standard ModeTools

33.50

9 / 12

τ²-Bench - Telecom

Standard ModeTools

14.90

258 / 264

τ²-Bench - Telecom

Thinking EnabledTools

31.60

207 / 264

Terminal Bench Hard

Standard ModeTools

12.10

178 / 244

Terminal Bench Hard

Thinking EnabledTools

13.60

173 / 244

Instruction Following

2 evaluations

Benchmark / mode

Score

Rank/total

IF Bench

Standard Mode

223 / 282

IF Bench

Thinking Enabled

50.30

156 / 282

Long Context

1 evaluations

Benchmark / mode

Score

Rank/total

AA-LCR

Standard Mode

49.90

139 / 171

Claw-style Agent Evaluation

1 evaluations

Benchmark / mode

Score

Rank/total

Pinch Bench

Thinking EnabledTools

70.70

32 / 38

Multimodal Understanding

3 evaluations

Benchmark / mode

Score

Rank/total

GeoBench ACW

Standard Mode

9 / 20

MMMU-Pro

Standard Mode

65.50

151 / 229

MMMU-Pro

Thinking Enabled

69.10

138 / 229

Other

1 evaluations

Benchmark / mode

Score

Rank/total

Fiction.liveBench

Standard Mode

77.80

9 / 16

Compare with other models