List your company

Review Generation on Board Game Playtesting Dataset

99.46FactualityGPT-5.1
58.286468.975779.66590.3543Jan 12, 2026

Evaluation results

MethodLinks
GPT-5.12026.0199.460.69344.26
Qwen3-235B2026.0198.950.65723.56
MeepleLM2026.0198.860.71174.34
Gemini3-Pro2026.0198.280.6483.98
Qwen3-8B2026.0197.880.59361.58
MeepleLMAblation=w/o Persona2026.0192.130.67713.56
MeepleLMAblation=w/o MDA2026.0191.560.6853.7
MeepleLMAblation=w/o Rulebook2026.0159.870.6973.3