docs: full-suite TB 2.1 — nano 64/89 ($1.31) vs pi 63/89 ($2.01) (PR 17) - #896
Merged
Conversation
The pi-matched full rerun (tb21-nano-flash-max-2: vision+websearch, deepseek-v4-flash max thinking, k=1) lands nano at 64/89 (71.9%) for $1.31 against pi's 63/89 (70.8%) for $2.01 and the pre-fix nano baseline's 60/89. Six of the eleven gained tasks are directly attributable to the shipped fixes (vision, websearch, care guideline, timeout-race mechanics); seven v1 passes flipped on k=1 build-time variance, so the honest read is parity-to-slight-edge on score with a durable ~35% cost advantage. Runbook carries the full table and the variance caveat; README banner and docs/nano.md updated. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Results of the pi-matched full rerun with the improvement PRs (#889–#894): nano 64/89 at $1.31 vs pi 63/89 at $2.01, baseline 60/89. Six gains mechanism-attributed, seven losses k=1 variance — documented as parity-to-slight-edge on score, durable ~35% cost advantage.
🤖 Generated with Claude Code