Unverified50% confidenceFactExact time
IGMBench covers two games, Minecraft and Terraria, contains 110 tasks, and defines more than 1.1K executable state and behavior judgment criteria.
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedExperiments 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.65% 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% similarUnverifiedIn agentic scenarios, large models can be used to generate high-quality task execution trajectories, which are then used to fine-tune models that are 10–100 times smaller in parameter count to perform specific subtasks.54% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/975621API
curl https://kongchang.com/api/v1/knowledge/claims/975621MCP
get_claim(id=975621)