Darwin-BRIGHT-Retriever
FINAL-Bench in-house retrieval system for the BRIGHT benchmark (reasoning-intensive information retrieval).
Internal method and components are not disclosed.
This repository records the evaluation results of the system. It does not contain model weights.
Evaluation
Measured with the MTEB evaluation framework on BRIGHT (v1.1), nDCG@10, under the public leaderboard protocol. Scores are published only after the full evaluation completes and is measured end to end.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Spaces using FINAL-Bench/Darwin-BRIGHT-Retriever 2
Evaluation results
- mteb/BRIGHT · BRIGHT V1 1 View evaluation results source leaderboard
