Delexa-7B: benchmark results
Provider: Other.
Aggregate Rating 1429 ± 43, rank #4725 of 10916 rated models, from 28 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open PL LLM - PolEmo2-OUT (multiple choice, 5-shot) | 74.29 | Accuracy (%) | 75.2 |
| Open PL LLM - DYK (multiple choice, 5-shot) | 60.4 | Binary F1 (%) | 68.9 |
| Open PL LLM - DYK (generative, 5-shot) | 62.07 | Binary F1 (%) | 68.2 |
| Open PL LLM - KLEJ NER (generative, 5-shot) | 49.22 | Accuracy (%) | 63.2 |
| Open PL LLM - PolQA Reranking (multiple choice, 5-shot) | 73.06 | Accuracy (%) | 60.8 |
| Open PL LLM - EQ-Bench | 32.16 | EQ-Bench Score | 56.7 |
| Open PL LLM - Multiple Choice | 42.88 | Average Multiple-Choice Score (%) | 56.6 |
| Open PL LLM - PSC (multiple choice, 5-shot) | 67.34 | Binary F1 (%) | 54.5 |
| Open PL LLM - RAG | 58.39 | Average RAG Score (%) | 54.5 |
| Open PL LLM - PolEmo2-OUT (generative, 5-shot) | 67.21 | Accuracy (%) | 53.8 |
| Open PL LLM Leaderboard | 45.31 | Average Score (%) | 53.8 |
| Open PL LLM - KLEJ NER (multiple choice, 5-shot) | 46.02 | Accuracy (%) | 50 |
Interactive version: theaggregate.ai/model?slug=delexa-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.