Public bake-off · classify

Best small model for Classify the sentiment of a customer message as positive or negative

Winner: distilbert/distilbert-base-uncased-finetuned-sst-2-english incumbent

Resident family incumbents were compared on the submitted labels.

Bake-off bo_ccf370b587991a6d6fbd96956869eab0 · 2026-08-19T16:34:55.408727Z

Are you the winning model’s author?

Add this exact line to the winner’s public Hugging Face README.md, then call the claim endpoint with its repo id.

Bay-Run-Claim: bo_ccf370b587991a6d6fbd96956869eab0 · sha256:3b33b74949b7f3adb821a3316b247f284e7bed84844fb6b2c1867a48b5f62898

Scorecard

Rank	Model	Metrics	Predicted vs expected	Latency	Status
1	`distilbert/distilbert-base-uncased-finetuned-sst-2-english`incumbentwinner	accuracy 1.0macro_f1 1.0n 5	Not retained	199 ms	scored
2	`cross-encoder/nli-deberta-v3-xsmall`incumbent	accuracy 1.0macro_f1 1.0n 5	Not retained	1523 ms	scored
—	`cardiffnlp/twitter-roberta-base-sentiment-latest`incumbent	No score	Not retained	1138 ms	failed

Signed receipt

This result is bound to its task, candidates, scorecard, and winner.

sha256:3b33b74949b7f3adb821a3316b247f284e7bed84844fb6b2c1867a48b5f62898

Winner badge

Copy-paste Markdown:

[![Bay Run bake-off winner · receipted](https://run.huggingbay.xyz/bakeoffs/bo_ccf370b587991a6d6fbd96956869eab0/badge.svg)](https://run.huggingbay.xyz/bakeoffs/bo_ccf370b587991a6d6fbd96956869eab0)

Reproduce it

The first bake-off is anonymous. Run the same labeled request directly:

curl -sS https://run.huggingbay.xyz/v1/bakeoff -H 'Content-Type: application/json' --data '{"task_description":"Classify the sentiment of a customer message as positive or negative","examples":[{"input":"I love this, works perfectly","expected":"positive"},{"input":"Broke after two days, terrible","expected":"negative"},{"input":"Support was fantastic","expected":"positive"},{"input":"Worst purchase I have made","expected":"negative"},{"input":"Exactly what I needed","expected":"positive"}]}'