Opus 5 Max burns ~3x tokens of Medium with little gain, staffer says
abeirami · x · 2026-08-27
Commenting on model evaluation practices, Abeirami notes observations often carry across benchmarks: Opus 5 Max burns roughly 3x the tokens of Opus 5 Medium without much gain — with the same per-token price, that makes it 3x more expensive overall. She recommends curating a set of tasks similar to your own work and comparing models on that.
Related event: Opus 5 Max burns 3x tokens of Medium for marginal gains(2 posts)→
More from Models
- Nat Lambert: wave of AI releases rumored — thinky, muse spark, Fable 5.5, OpenAI — natolambert · 2026-10-15
- Musk amplifies dev's verdict: Grok Bot easier to use than Codex and Claude — elonmusk · 2026-10-15
- Rumor: New Anthropic model imminent, apparently behind a batch of high-severity Chrome CVEs — matthew_d_green · 2026-10-15
- StartLux-Decision debuts RL-trained calibrated decision models, 27B scores 72.8 — startlux-models · 2026-10-15
- Meta's Muse Code slammed for harsh quotas: 21% left after 5 hours — ThomasScialom · 2026-10-15
- Claude Code error mentions 'Fable 5.1' and 'Opus 5', hinting at unreleased models — adonis_singh · 2026-10-15