Qwen3-Coder-Next Benchmark Details

Qwen3-Coder-Next currently shows benchmark results led by SWE-bench Verified (48 / 103, score 70.60), Aider-Polyglot (14 / 26, score 66.20), Pinch Bench (25 / 37, score 79.10).

Benchmark Results

Qwen3-Coder-Next

Benchmark Results

编程与软件工程

2 evaluations

Benchmark / mode

Score

Rank/total

SWE-bench Verified

Standard ModeTools

70.60

48 / 103

SWE-Bench Pro - Public

Standard ModeTools

44.30

28 / 36

Agent能力评测

1 evaluations

Benchmark / mode

Score

Rank/total

Aider-Polyglot

Standard ModeTools

66.20

14 / 26

AI Agent - 工具使用

1 evaluations

Benchmark / mode

Score

Rank/total

Terminal Bench 2.0

Standard ModeTools

36.20

42 / 43

OpenClaw智能体能力综合测评

2 evaluations

Benchmark / mode

Score

Rank/total

Pinch Bench

Thinking EnabledTools

79.10

25 / 37

Claw Bench

Thinking EnabledTools

75.80

24 / 29

Compare with other models