gb2-20260926-80fec42d483b

DuelLab GameBench 2 evaluates AI-generated game-playing programs through deterministic head-to-head matches. Match outcomes, not human or AI judges, produce the ratings. Public standings, methodology, and release data are available; the evaluator, engine implementation, and unpublished operational artifacts remain private.

Generated
Benchmark version
2-known8-r3
Games
8
Models
73
Reasoning variants
200
Rated matches
209502

GameBench 1 and GameBench 2 use different game sets and evaluation contexts; their scores and ranks are not directly comparable.

Data and checksums

Leaderboard JSON index (rows in per-leaderboard files under leaderboard/) · Leaderboard CSV · Leaderboard Parquet · Entrants JSON · Charts data · Data dictionary

Release manifest and SHA-256 checksums · Licensed under CC BY 4.0.

Release lineage and package-ID mapping explains when multiple immutable package IDs contain the same canonical result data.

A living copy of the public results is available from the DuelLab GameBench 2 results mirror on Hugging Face. This immutable DuelLab release remains canonical.

Citation files

BibTeX · CSL-JSON · RIS · CITATION.cff · Plain text

The canonical citation authority is https://duellab.org/citation.