LLM Skirmish
Benchmarks where LLMs write code to play strategy games
LLM Skirmish is a benchmarking platform for evaluating large language models by having them write game-playing code. Models are tested on strategy games, with results published as leaderboards and benchmarks.
11 alternatives to LLM Skirmish
Ranked by how well each tool replaces LLM Skirmish: shared features, audience, price and popularity.
Multi-LLM boardrooms with shared memory and an auditable decisions log
Covers 0 of 10 key features.
Free plan54 out of 100 matchFreeFree, open-source, no-code game engine for 2D and 3D games
Covers 1 of 10 key features and is open source.
Free planOpen source54 out of 100 matchFreeMonitoring and evaluation platform for LLM developers
Covers 0 of 10 key features and is open source.
Free planOpen source45 out of 100 matchFree- 41 out of 100 match—
Search local LLM hardware requirements — find out exactly what hardware you need to run a
Covers 1 of 10 key features.
Free plan41 out of 100 matchFree- 41 out of 100 matchFree
Frontier training data, RL environments and benchmarks graded by experts
Covers 1 of 10 key features.
37 out of 100 matchContact sales