DVMap — leaderboard
Metric: Accuracy (self-reported). Source: benchmarklist.com. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 48.5 |
| 2 | Qwen 3 Next 80B A3B | 47.6 |
| 3 | Llama 3.3 70B Instruct | 46.4 |
| 4 | GPT-4o Mini | 46.3 |
| 5 | Qwen 3 14B | 46.2 |
| 6 | Gemini 2.5 Flash Lite | 45.3 |
| 7 | DeepSeek V3.2 Exp | 45.1 |
| 8 | Claude 3.7 Sonnet | 26.9 |
Interactive version: theaggregate.ai/benchmark?slug=dvmap · How the rankings work · Data refreshed daily, snapshot 2026-07-22.