Individual benchmark scores plotted by date.
| Organisation | Model | Reported | Top Score | Info | Self Reported | Source |
|---|---|---|---|---|---|---|
| DeepSeek V4 Pro | 24 Apr 2026 | 84.40% | Best reported mode. Non-think: 75.8, High: 77.7, Max: 84.4 | Yes | Source | |
| DeepSeek V4 Flash | 24 Apr 2026 | 78.90% | Best reported mode. Non-think: 71.5, High: 73.2, Max: 78.9 | Yes | Source |
