Unverified50% confidenceBenchmarkExact time
Experiments were conducted on GameCraft Bench, a benchmark containing 140 game development tasks covering 15 game series, with identical tasks implemented on both the Godot and Phaser engines.
1
Sources
50%
Confidence
Long-term
Relevance
10/2/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedPilot experiments had three coding agents and eight models each run eight 20-minute single-pass tasks, with label-aware F1 showing extremely high variance ranging from 0.143 to 0.892.58% similarUnverifiedThe experiment proceeded in stages: first nine functional features, then six more challenging tasks, followed by fifteen additional changes (including modifications to earlier requirements), with the Java code of the two projects reaching approximately 12k and 15k lines respectively in the later stages.56% similarUnverifiedGameJam活动参与者通常需具备至少一项编程或设计技能，才能在48至72小时内完成可演示的原型55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/968725API
curl https://kongchang.com/api/v1/knowledge/claims/968725MCP
get_claim(id=968725)