SOLAR-Platypus-10.7B-v1: benchmark results
SOLAR fine-tune on Open-platypus-Commercial with rank-16 MLP-target LoRA and Alpaca template; not an Upstage release. Provider: kyujinpy. Access: Open.
Aggregate Rating 1393 ± 36, rank #6412 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 82.79 | Accuracy (%) (5-shot) | 85.6 |
| Open LLM Leaderboard v1 - HellaSwag | 84.23 | Normalized accuracy (%) (10-shot) | 64.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 61.69 | Normalized accuracy (%) (25-shot) | 53.9 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 51.58 | MC2 (%) (0-shot) | 52.5 |
| Open LLM Leaderboard v1 - MMLU | 60.37 | Accuracy (%) (5-shot) | 47.9 |
| Open LLM Leaderboard v1 - GSM8K | 11.07 | Accuracy (%) (5-shot) | 32.3 |
Interactive version: theaggregate.ai/model?slug=solar-platypus-10-7b-v1 · How It Works · Data refreshed daily, snapshot 2026-11-08.