A model leaderboard shows Fable scores stay stable while rankings barely move
cis_female · x · 2026-07-22
A ranking table shows Fable-style scores stay mostly stable across runs
The post says there is some grading variability in Fable, but not much, and the rankings remain mostly the same.
The attached chart shows a model leaderboard with mean score, standard deviation, and letter grade. It ranks models such as anthropic/claude-opus-4.8, meta/muse-spark-1.1, openai/gpt-5.6-sol, z-ai/glm-5.2, google/gemini-3.5-flash, and x-ai/grok-4.20.
The reply adds a cost-based angle: people had been treating muse spark and grok-4.20 as roughly equivalent cheap-good models, but this table suggests muse spark is near the top while grok is far lower.
Related event: Testing LLMs on Relationship Understanding with 600k Tokens(6 posts)→
More from Models
- Leaked Terminal-Bench 4.0 chart shows GPT-6.1 Terra leading at lowest cost, unverified — Angaisb_ · 2026-10-27
- GPT-6.1 Terra rolls out to all Plus, Pro, Enterprise and Edu users — OpenAI · 2026-10-27
- OpenAI launches GPT-6.1 Terra with 50% lower API prices than GPT-5.6 Terra — OpenAI · 2026-10-27
- In cyber, intention matters little: Chintala on model info leaks, and what users should do — brhydon · 2026-10-27
- Why don't more LLMs ship 10M-token context? A researcher asks about attention tradeoffs — agarwl_ · 2026-10-27
- Ortet's first health eval: 34 open-weight models, 50 tasks, generic rankings fall short — thegautamkamath · 2026-10-27