Repository navigation
Land BizRouter submission (#229) with price-table conflicts resolved - #245
Merged
Merged
Conversation
Production BizRouter balanced routing policy, one API call per prompt. Adds the router config, full (8,400) and robustness (420) predictions, list prices for 17 pool models, and their universal names. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
XM-Dong
pushed a commit
to XM-Dong/RouterArena
that referenced
this pull request
Oct 30, 2026
BizRouter's production balanced policy (RouteWorks#229, landed via RouteWorks#245): Arena 77.04, accuracy 81.61%, $1.00 per 1K queries, robustness 97.38, re-evaluated with the LiveCodeBench fixes. Adds its README row and a closed-source manifest entry for the website; every other row moves down one place. Co-Authored-By: Claude Opus 5.5 <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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Lands BizRouter (#229) by @iziz. It is the PR's own commits plus one merge commit that resolves its conflicts with main. GitHub's token can't push to the contributor's fork, so the resolution comes through this branch. Once this merges, #229 is marked as merged.
Conflict resolution: after Divyam (#232) merged, both PRs had appended to
model_cost/model_cost.jsonanduniversal_model_names.py. Both sides are kept: main's entries, including #232'sgemini-3.8-flash, plus BizRouter's 17 entries. No shared key has a different price.check_config_prediction_files.py BizRouter fullandrobustnesspass on the merged tree.Submission: production gateway, balanced policy. Re-evaluated on Oct 29 with the LiveCodeBench fixes: Arena 0.7704, accuracy 81.61%, $1.00/1K, robustness 0.9738, 5 content-filter refusals kept as failures. Audited clean: no copied answers and normal token counts. Its main model, gemini-3.7-flash, has no other sample in the repo to compare against.
Prices are as submitted. Every router's prices will be revisited together when the price table is rebuilt.
🤖 Generated with Claude Code