Board game eval: Fable underperforms vs Opus 5
xeophon · x · 2026-08-25
The author created an online version of the strategic horse-betting board game 'Long Shot' and tested various models. Results show that Fable performs significantly worse than Opus 5 in the default game mode.
More from Models
- Image comparison: Opus 5 benchmark cost significantly lower than GPT 5.6 Sol — dejavucoder · 2026-08-25
- LLM testing: Opus best for teaching, domestic models offer high value for coding — Yuchenj_UW · 2026-08-25
- Kimi unveils new attention: 6x faster inference, 75% less GPU memory — pstAsiatech · 2026-08-25
- Qwen 3.8 27B generates realistic WebGL ocean in 4 hours — BlackBeardAI · 2026-08-25
- Venice.ai reportedly integrates Gemma 4 Uncensored model — EnigmaFund · 2026-08-25
- Debate over DeepSeek V4 code design, claims it is not distilled from Opus — MaziyarPanahi · 2026-08-25