GitHub Repository

A multi-agent benchmark where eight LLMs play a money-driven elimination game with private transfers and a buyout endgame, and are ranked by final wealth

16 stars

Buyout Game Benchmark: Multi-Agent Bargaining, Transfers, and Takeovers

Name: Buyout Game Benchmark: Multi-Agent Bargaining, Transfers, and Takeovers
Availability: InStock
Author: zone411

by zone411·Mar 30, 2026·6 points·0 comments

Visit Project View on HN

AI Analysis

●●SolidBig BrainNiche Gem

Wealth-based scoring reveals strategic failures that survival-only benchmarks miss.

Strengths

•Private transfers plus public votes creates genuine coalition pricing dynamics.
•Bradley-Terry ranking over mirrored match packs ensures statistical rigor.
•Final wealth vs finish order exposes models that survive but overspend.

Weaknesses

•Niche audience—LLM benchmarking is crowded with established frameworks.
•No API or programmatic access to run custom model evaluations yet.

Similar Projects

AI/ML●●Solid

NetHack agent harness with benchmarks and livestream

You can watch an LLM play NetHack step-by-step with the model's reasoning, the exact action code, and a live game canvas — that instrumentation is the product's real selling point. The leaderboard + run/benchmark framing makes it useful for comparing agents rather than just a flashy demo, but it's still squarely for people who care about NetHack or agent evaluation; more detail on reproducible metrics and integrations would push it further.

Niche GemWizardry

kenforthewin

113mo ago

AI/ML●Mid

CivBench a long-horizon AI benchmark for multi-agent games

Civilization matches expose model divergence that static benchmarks miss—but it's a spectacle, not a measurement.

Rabbit HoleBig Brain

mbh159

12243mo ago

AI/ML●●●Banger

Rogue-Bench – LLMs play the game Rogue

Using 1980s Rogue as an LLM benchmark is genuinely novel and technically clever.

WizardryZero to One

iwhalen

108d ago

AI/ML●●●Banger

Benchmarking LLMs through autonomous games of Blood on the Clocktower

Social deduction games test deception and theory of mind better than standard benchmarks.

Rabbit HoleCrowd PleaserZero to One

cjami

102mo ago

AI/ML●●●Banger

Republic of Agents: Benchmark for Social Reasoning in LLMs

Mafia-as-benchmark with learning-between-batches mechanism; public, inspectable sessions.

Zero to OneBig BrainWizardry

kkonstantin

102mo ago

AI/ML●●Solid

A real-time strategy game that AI agents can play

Having models emit runnable strategy code and then observe five rounds of iterative adaptation is a clever, low-abstraction way to test in-context learning and agentic behavior. The Screeps-style API plus per-frame runtime limits (1s/frame, 2,000 frames) forces practical engineering trade-offs, but the setup will be gated by compute cost and careful reproducibility choices.

WizardryBig BrainNiche Gem

__cayenne__

413mo ago