Qwen3-Omni-30B-A3B Benchmark Details

Qwen3-Omni-30B-A3B currently shows benchmark results led by LiveCodeBench (99 / 251, score 67.90), AIME2025 (111 / 215, score 74), GPQA Diamond (304 / 461, score 72.60).

Benchmark Results

Qwen3-Omni-30B-A3B

Benchmark Results

Knowledge Exams

1 evaluations

Benchmark / mode

Score

Rank/total

HLE

Thinking Mode

7.50

438 / 568

Scientific Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Thinking Mode

72.60

304 / 461

Algorithmic Coding

1 evaluations

Benchmark / mode

Score

Rank/total

LiveCodeBench

Thinking Mode

67.90

99 / 251

Mathematics

1 evaluations

Benchmark / mode

Score

Rank/total

AIME2025

Thinking Mode

111 / 215

Service Workflows

1 evaluations

Benchmark / mode

Score

Rank/total

τ²-Bench - Telecom

Thinking ModeTools

21.30

243 / 264

Instruction Following

1 evaluations

Benchmark / mode

Score

Rank/total

IF Bench

Thinking Mode

43.40

190 / 282

Agentic Development

1 evaluations

Benchmark / mode

Score

Rank/total

Terminal Bench Hard

Thinking ModeTools

3.80

219 / 244

Visual Understanding

1 evaluations

Benchmark / mode

Score

Rank/total

MMMU-Pro

Thinking Mode

60.20

176 / 229

Compare with other models