feat(assistant): upgrade default models to gpt-5.4-nano and gpt-5.3-codex#2554
Draft
everettbu wants to merge 1 commit into
Draft
feat(assistant): upgrade default models to gpt-5.4-nano and gpt-5.3-codex#2554everettbu wants to merge 1 commit into
everettbu wants to merge 1 commit into
Conversation
everettbu
added
the
run-evals
Contributor
Braintrust eval reportEvals failed: Error: Command failed with exit code 1 |
Contributor
🎭 Playwright Test Results
Details
Skipped testsFeatures › assistant.spec.ts › AI Assistant › Can send a message to the assistant and receive a response |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Mirror of supabase/supabase#43887
Original author: mattrossman
Upgrades the assistant's default OpenAI models:
gpt-5-mini→gpt-5.4-nano— newer gen, cheaper (0.8× input / 0.625× output), better coding benchmarks (+6.7pp SWE-bench Pro)gpt-5→gpt-5.3-codex— coding-specialized, +15pp SWE-bench Pro, 25% faster, 1.4× cost increaseEvals show no quality regressions across all scorers (completeness, goal completion, tool usage, SQL validity all flat). Token usage and latency improved significantly with nano.
Closes AI-509