bagel-dpo-34B-v0.2: benchmark results
Provider: Jon Durbin. Released 2024-01-01. Access: Open.
Unified ELO 1604 ± 32, rank #615 of 2656 rated models, from 13 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Portuguese LLM - FaQuAD NLI | 83.86 | Macro F1 (%) | 97.4 |
| Open Chinese LLM - ARC Challenge | 64.42 | Accuracy (%) | 96.1 |
| Open Chinese LLM - CMMLU | 72.06 | Accuracy (%) | 94.4 |
| Open Chinese LLM - C-Eval Semantic | 90.03 | Accuracy (%) | 92.6 |
| Open Chinese LLM - HellaSwag | 69.58 | Accuracy (%) | 91.7 |
| Open Chinese LLM - WinoGrande | 70.01 | Accuracy (%) | 91.5 |
| Open Portuguese LLM - BLUEX | 66.9 | Accuracy (%) | 89.4 |
| Open Chinese LLM Leaderboard | 68.07 | Average Score (%) | 89.3 |
| Open Chinese LLM - TruthfulQA MC | 60.61 | Accuracy (%) | 84.3 |
| Open Portuguese LLM - OAB Exams | 53.03 | Accuracy (%) | 82.9 |
| Open Portuguese LLM - ENEM | 71.94 | Accuracy (%) | 81.7 |
| Open Portuguese LLM - ASSIN2 RTE | 91.53 | Macro F1 (%) | 67.7 |
Interactive version: theaggregate.ai/model?slug=bagel-dpo-34b-v0-2 · How It Works · Data refreshed daily, snapshot 2026-09-19.