Effort levels recalibrated in Opus 4.8
SWE-Bench Pro system card data shows a major shift in token consumption. The low-effort setting in Opus 4.8 now uses as many output tokens as the medium or high settings in 4.7 and 4.6.
The efficiency of Opus 4.8 on low effort matches the high level of 4.7. The medium setting in 4.8 consumes more tokens than the high setting in 4.7, approaching the absolute maximum of 4.6.
Developers should reassess generation settings. Increased token consumption directly impacts API speed and cost.
Up next
Claude Code update 2.1.157
Claude Code 2.1.157 lets you load plugins straight from your project folder. No more publishing to the marketplace just to test local tools. This streamlines building custom skills to automate routine tasks. You can now assemble and run your own agent locally in minutes.
Related stories
- Haiku 5.5 ranks #2 of 182 and burns 440M tokens doing it
- Sonnet 5.5 hits third place by writing 410M tokens
- Sonnet 5.5 edges past Opus 5.5 on Terminal-Bench 4.0
- Max effort adds nothing to Fable 5.1’s ARC-AGI-2 score
- Opus 5 tops Fable 5 on OSWorld 2.0 at a third of the price
- Claude Fable 5: access and capabilities
Comments
No comments yet. Be the first.
Join the conversation
Sign in to leave a comment. It appears after moderation.