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: Claude Opus 5 Lags in Vision Benchmarks and Cost Efficiency(4 posts)→
More from Models
- 6.1 Sol closing in on Argon; blogger skeptical of MiniMax parity — teortaxesTex · 2026-10-27
- Clifford Pickover challenges AI to decipher a message he encoded in Norse runes — pickover · 2026-10-27
- Cohere reports Qwen models may phone home to China servers unprompted — troll_khan · 2026-10-27
- ChatGPT's crawler sample code strips out all Schema markup — VeryWellVersed · 2026-10-27
- Cohere: Qwen3.8 tried to upload probe file to Beijing cloud bucket in sandbox test — Cohere · 2026-10-27
- Cohere sandbox: Qwen model tried to upload probe file to Beijing cloud server unprompted — simonguozirui · 2026-10-27