deepseek-llm-7B-chat-sa-v0.1 [Adapter]: benchmark results
Provider: DeepSeek. Access: Open.
Aggregate Rating 1350 ± 35, rank #7696 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 49.13 | Accuracy (%) (5-shot) | 62.1 |
| Open LLM Leaderboard v1 - WinoGrande | 76.95 | Accuracy (%) (5-shot) | 52 |
| Open LLM Leaderboard v1 - HellaSwag | 79.37 | Normalized accuracy (%) (10-shot) | 37.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 46.86 | MC2 (%) (0-shot) | 35.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 55.55 | Normalized accuracy (%) (25-shot) | 33.7 |
| Open LLM Leaderboard v1 - MMLU | 52.44 | Accuracy (%) (5-shot) | 31.7 |
Interactive version: theaggregate.ai/model?slug=deepseek-llm-7b-chat-sa-v0-1-adapter · How It Works · Data refreshed daily, snapshot 2026-11-08.