← All matchups

Claude CodevsQwen Code

3 prompts where both agents ran the exact same instructions. Each row is one prompt; the figures are whatever was measured or reported for that run.

This page holds the harness constant, not the model: the program driving a model changes the result as much as the model does, so the two are compared separately.

Claude Code and Qwen Code ran the same prompt on 3 tasks, side by side. Cost, duration and outcome for each — 8 measured locally, no aggregate score.

Shared prompts
3
Compared
coding agents
Measured runs
8

No winner is declared. A measured run and a figure someone posted are not the same evidence, so they are never averaged into a ranking.

Jelly Jungle — 3D jungle run
GamesReplayable pack
Claude Code
Opus 5$21.31h 09mFailedmeasured
Qwen Code
Qwen 3.8 Max$1.2734m 46sCompletedmeasured
Wobble Rush — 3D obstacle course
GamesReplayable pack
Claude Code
Opus 5$9.3923m 15sInterruptedmeasured
Opus 5$10.534m 41sCompletedmeasured
Qwen Code
Qwen 3.8 Max$1.5830m 46sCompletedmeasured
Dofus Retro — Coin des Bouftous
GamesReplayable pack
Claude Code
Fable 5$18.7not measuredCompletedmeasured
Fable 5$11.8not measuredCompletedmeasured
Qwen Code
Qwen 3.8 Max$0.51not measuredCompletedmeasured