SauerkrautLM-SOLAR-Instruct: benchmark results
A VAGOsolutions German-English DPO fine-tune of upstage/SOLAR-10.7B-Instruct-v1.0 using Sauerkraut preference data, translated UltraFeedback data and distilabel mathematical preferences. Provider: VAGOsolutions. Access: Open.
Aggregate Rating 1455 ± 32, rank #3563 of 10916 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 88.63 | Normalized accuracy (%) (10-shot) | 93.2 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 71.95 | MC2 (%) (0-shot) | 92.7 |
| Open LLM Leaderboard v1 - WinoGrande | 83.5 | Accuracy (%) (5-shot) | 89.2 |
| Open LLM Leaderboard v1 - ARC Challenge | 70.82 | Normalized accuracy (%) (25-shot) | 87 |
| Open LLM Leaderboard v1 - MMLU | 66.2 | Accuracy (%) (5-shot) | 86.3 |
| Open LLM Leaderboard v1 - GSM8K | 64.14 | Accuracy (%) (5-shot) | 77.8 |
| Open LLM Leaderboard - GPQA | 30.54 | Score | 62.2 |
| Open LLM Leaderboard - IFEval | 49.17 | Score | 57.5 |
| Open LLM Leaderboard - BBH | 51.69 | Score | 57.3 |
| Open LLM Leaderboard - MMLU-Pro | 31.83 | Score | 43.3 |
| Open LLM Leaderboard - MuSR | 39.65 | Score | 39.1 |
| Open LLM Leaderboard - MATH Level 5 | 6.34 | Score | 34.5 |
Interactive version: theaggregate.ai/model?slug=sauerkrautlm-solar-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.