Qwen3-4B-2507 Benchmark Details

Qwen3-4B-2507 currently shows benchmark results led by GPQA Diamond (224 / 274, score 62), AIME2025 (90 / 107, score 47.40), LiveCodeBench (113 / 128, score 35.10).

Benchmark Results

Qwen3-4B-2507

Benchmark Results

Other

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

62

224 / 274

Coding and Software Engineer

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

35.10

113 / 128

Math and Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

47.40

90 / 107

Compare with other models