Qwen3.5-9B Benchmark Details

Qwen3.5-9B currently shows benchmark results led by C-Eval (8 / 48, score 88.20), MMLU Pro (52 / 133, score 82.50), GPQA Diamond (130 / 270, score 81.70).

Benchmark Results

Qwen3.5-9B

Benchmark Results

General Knowledge

2 evaluations

Benchmark / mode

Score

Rank/total

C-Eval

Thinking Enabled

88.20

8 / 48

MMLU Pro

Thinking Enabled

82.50

52 / 133

Other

2 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Standard Mode

78.91

151 / 270

GPQA Diamond

Thinking Enabled

81.70

130 / 270

Coding and Software Engineer

1 evaluations

Benchmark / mode

Score

Rank/total

LiveCodeBench

Thinking Enabled

65.60

66 / 127

Instruction Following

1 evaluations

Benchmark / mode

Score

Rank/total

IF Bench

Thinking Enabled

64.50

24 / 34

Text Embedding

2 evaluations

Benchmark / mode

Score

Rank/total

Context Arena

Standard Mode

22.60

121 / 126

Context Arena

Thinking Enabled

43.28

97 / 126

Long Context

2 evaluations

Benchmark / mode

Score

Rank/total

AA-LCR

Thinking Enabled

24 / 27

LongBench v2

Thinking Enabled

55.20

11 / 13

Compare with other models