Individual benchmark scores plotted by date.
| Organisation | Model | Reported | Top Score | Info | Self Reported | Source |
|---|---|---|---|---|---|---|
| DeepSeek V4 Pro | 24 Apr 2026 | 38.30% | Best reported mode. Non-think: 0.4, High: 27.4, Max: 38.3 | Yes | Source | |
| DeepSeek V4 Flash | 24 Apr 2026 | 33% | Best reported mode. Non-think: 1.0, High: 19.1, Max: 33.0 | Yes | Source |
