Sakura-SOLRCA-Instruct-DPO: benchmark results
Sakura DPO release using Intel orca_dpo_pairs, distinct from math-preference DPO release. Provider: Other. Access: Open.
Aggregate Rating 1460 ± 37, rank #3319 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 72.1 | MC2 (%) (0-shot) | 93.1 |
| Open LLM Leaderboard v1 - HellaSwag | 88.49 | Normalized accuracy (%) (10-shot) | 92.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 71.16 | Normalized accuracy (%) (25-shot) | 88.2 |
| Open LLM Leaderboard v1 - WinoGrande | 82.95 | Accuracy (%) (5-shot) | 86.4 |
| Open LLM Leaderboard v1 - MMLU | 66.17 | Accuracy (%) (5-shot) | 86.1 |
| Open LLM Leaderboard v1 - GSM8K | 63.46 | Accuracy (%) (5-shot) | 76.8 |
Interactive version: theaggregate.ai/model?slug=sakura-solrca-instruct-dpo · How It Works · Data refreshed daily, snapshot 2026-11-08.