feat(router): v0.54 cluster artifact for RouterArena leaderboard submission#232
Open
steventohme wants to merge 1 commit into
Open
feat(router): v0.54 cluster artifact for RouterArena leaderboard submission#232steventohme wants to merge 1 commit into
steventohme wants to merge 1 commit into
Conversation
…ission Adds v0.54 cluster bundle and promotes it to `latest`. Trained from v0.53 on OpenRouterBench labels + AA quality priors; no RouterArena prompts in any training signal (the previous leaderboard submission was invalidated for eval-set contamination, so per-source data lineage is documented in metadata.yaml's `training_data` block). Offline arena_score_beta_0_1 = 75.79 on the 8,400-prompt RouterArena full split (vs prior 72.90).
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds
v0.54cluster bundle and promotes it tolatest. Trained fromv0.53on OpenRouterBench labels + AA quality priors; no RouterArenaprompts in any training signal (the previous leaderboard submission
was invalidated for eval-set contamination, so per-source data lineage
is documented in
metadata.yaml'straining_datablock).Offline
arena_score_beta_0_1 = 75.79on the 8,400-prompt RouterArenafull split (vs prior 72.90).
🤖 Generated with Claude Code