SOLID-SFT-DPO-MixQV2-SOLIDRejected-SFTChosen-Zephyr-7B-beta: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1372 ± 34, rank #7112 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 52.36 | MC2 (%) (0-shot) | 55.5 |
| Open LLM Leaderboard v1 - MMLU | 60.14 | Accuracy (%) (5-shot) | 47 |
| Open LLM Leaderboard v1 - ARC Challenge | 58.96 | Normalized accuracy (%) (25-shot) | 41.5 |
| Open LLM Leaderboard v1 - GSM8K | 19.03 | Accuracy (%) (5-shot) | 40.3 |
| Open LLM Leaderboard v1 - HellaSwag | 79.82 | Normalized accuracy (%) (10-shot) | 39.2 |
| Open LLM Leaderboard v1 - WinoGrande | 73.24 | Accuracy (%) (5-shot) | 31.5 |
Interactive version: theaggregate.ai/model?slug=solid-sft-dpo-mixqv2-solidrejected-sftchosen-zephyr-7b-beta · How It Works · Data refreshed daily, snapshot 2026-11-08.