deepseek-math-7B-instruct [float16] [rev: 0a5828f800a3]: benchmark results
Provider: DeepSeek. Access: Open.
Aggregate Rating 1334 ± 36, rank #8086 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 20.85 | Accuracy (%) (5-shot) | 41.6 |
| Open LLM Leaderboard v1 - MMLU | 56.55 | Accuracy (%) (5-shot) | 39.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 53.58 | Normalized accuracy (%) (25-shot) | 29.8 |
| Open LLM Leaderboard v1 - HellaSwag | 71.53 | Normalized accuracy (%) (10-shot) | 21.7 |
| Open LLM Leaderboard v1 - WinoGrande | 65.98 | Accuracy (%) (5-shot) | 19.6 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 40.38 | MC2 (%) (0-shot) | 13.9 |
Interactive version: theaggregate.ai/model?slug=deepseek-math-7b-instruct-float16-rev-0a5828f800a3 · How It Works · Data refreshed daily, snapshot 2026-11-08.