docs: Context 0.4.0 cost screen on DeepSeek V4 Pro - #32
Merged
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Locked single-arm cost screen of the 0.4.0 release build (24 cells, no failures, no retries) against the recorded plain and Graphify cells.
Result: does not pass. Geometric mean input ratio 1.086 against plain (90% interval 0.831 to 1.271) and 1.219 against Graphify (1.007 to 1.536). Tool errors fell to 13 of 619 and turns fell on six of eight tasks, but diagnosis-context rose to 4.2 to 4.9M input over 70 to 80 turns.
See
docs/experiments/screen-pro-040-20260923/RESULTS.md.🤖 Generated with Claude Code
https://claude.ai/code/session_01KzXbuBSq88i3Re82qt6c4L