[KongchangAI]
Benchmark

GameFeel RE

A benchmark covering programming and game design tasks, used to evaluate the capabilities of large language models in code generation and game logic implementation.

Timeline (last 90 days)

Nov 18

On the GameFeel RE benchmark (covering more than 8,000 programming and game design tasks), Qwen 4 Max Preview scored 10.3.

Unverified50%
Nov 18

On the GameFeel RE technical chart, the unreleased variant Qwen 427B Early (codename QDuck) scored 14.9, surpassing Sonnet 5.5 Extra High's 14.3.

Unverified50%

All Facts (2)

Source Articles