deepseek-llm-67B-chat [bfloat16] [rev: 79648bef7658]: benchmark results
Provider: DeepSeek. Access: Open.
Aggregate Rating 1473 ± 33, rank #2788 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 72.19 | Accuracy (%) (5-shot) | 95.3 |
| Open LLM Leaderboard v1 - WinoGrande | 84.21 | Accuracy (%) (5-shot) | 92.4 |
| Open LLM Leaderboard v1 - HellaSwag | 86.8 | Normalized accuracy (%) (10-shot) | 83 |
| Open LLM Leaderboard v1 - ARC Challenge | 67.75 | Normalized accuracy (%) (25-shot) | 78 |
| Open LLM Leaderboard v1 - GSM8K | 62.32 | Accuracy (%) (5-shot) | 75.5 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 55.83 | MC2 (%) (0-shot) | 66.3 |
Interactive version: theaggregate.ai/model?slug=deepseek-llm-67b-chat-bfloat16-rev-79648bef7658 · How It Works · Data refreshed daily, snapshot 2026-11-08.