Fable 5 reaches 67.3% on GameDevBench, trailing only GPT-5.6 Sol
scaling01 · x · 2026-07-24
Fable 5 tops GameDevBench with 67.3% task success, behind only GPT-5.6 Sol
A shared benchmark graphic says Fable 5 is now the best model on GameDevBench among the listed entries, with a 67.3% task success rate.
The same chart shows it:
- Beats every model except GPT-5.6 Sol
- Sits above several GPT-5.6 Sol variants and Claude Opus 4-8
- Represents a big jump from a few months ago, when models reportedly could not even break 50%
More from coding & agent
- Gergely Orosz: Shipping 10x PRs With AI Agents, Sites Fill With Small Regressions — ducha_aiki · 2026-09-11
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Astra storyboards plus Minimax H3 per-shot generation boost video success rates — Hailuo_AI · 2026-09-11
- Codex tip: use Sol with Astra and Luna sub-agents to save usage — pvncher · 2026-09-11
- agents-best-practices: a provider-neutral Agent Skill for designing and auditing agentic harnesses — tom_doerr · 2026-09-11
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11