Qwen3-Coder-Next Benchmark Details

Qwen3-Coder-Next currently shows benchmark results led by SWE-bench Verified (38 / 90, score 70.60), Aider-Polyglot (14 / 26, score 66.20), SWE-Bench Pro - Public (11 / 19, score 44.30).

Benchmark Results

Qwen3-Coder-Next

Benchmark Results

编程与软件工程

2 evaluations

Benchmark / mode

Score

Rank/total

SWE-bench Verified

OffWith tools

70.60

38 / 90

SWE-Bench Pro - Public

OffWith tools

44.30

11 / 19

Agent能力评测

1 evaluations

Benchmark / mode

Score

Rank/total

Aider-Polyglot

OffWith tools

66.20

14 / 26

AI Agent - 工具使用

1 evaluations

Benchmark / mode

Score

Rank/total

Terminal Bench 2.0

OffWith tools

36.20

24 / 25

Compare with other models