Opus 5 ran about 14% cheaper than Fable 5 on EyeBench-V3, despite using 2.5× more output tokens
adonis_singh · x · 2026-07-25
A follow-up EyeBench-V3 chart says Opus 5 ran about 14% cheaper than Fable 5 overall, mainly because it produced roughly 2.5× more output tokens.
The graphic breaks down the cost dynamics between the two models, showing that Fable is much terser, which narrows the raw run-cost gap.
Related event: Opus 5 is 14% Cheaper Than Fable 5 but Generates 2.5x Tokens(2 posts)→
More from Models
- Opus 5 beats Fable 5 on six agentic benchmarks, suggesting a split-role setup — daniel_mac8 · 2026-07-25
- A model eval can matter more for who finishes second than for who wins — ziv_ravid · 2026-07-25
- Artificial Analysis chart says Claude Opus 5 costs about 2× GPT 5.6 Sol per task — soumitrashukla9 · 2026-07-25
- Claude Opus 5 is now available in Hermes Agent via Nous Portal and OpenRouter — NousResearch · 2026-07-25
- An Opus 5 meme turns “a rose” into a tensor joke — liminal_bardo · 2026-07-25
- Early Opus 5 access suggests the model is fast, but too eager at high reasoning — alliekmiller · 2026-07-25