DeepSeek-V3 671B: benchmark results
Provider: DeepSeek.
Aggregate Rating 1659 ± 50, rank #560 of 10916 rated models, from 5 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| PARROT - Dialect Compatibility | 50.64 | Accuracy (%) | 85.7 |
| PARROT - MySQL Dialect Compatibility | 55.88 | Accuracy (%) | 85.7 |
| PARROT - Oracle Dialect Compatibility | 51.72 | Accuracy (%) | 71.4 |
| Wolfram LLM Benchmarking Project | 50.6 | Correct Functionality (%) | 63.3 |
| PARROT - Result Consistency | 32.65 | Accuracy (%) | 62.5 |
Interactive version: theaggregate.ai/model?slug=deepseek-v3-671b · How It Works · Data refreshed daily, snapshot 2026-11-08.