DROP
Can the model solve difficult problems that require more than factual recall?
Reasoning3 ranked models3 reported values1 reportsHigher is better
Top rankings
One row per model, using its best reported score across effort settings.
| Rank | Model | Best score | Best reported setting |
|---|---|---|---|
| 1 | DeepSeek-V4-Pro-BaseDeepSeek | 88.7% | Reported configurationDeepSeek report1 value · 1 reportApr 26, 2026 · source |
| 2 | DeepSeek-V4-Flash-BaseDeepSeek | 88.6% | Reported configurationDeepSeek report1 value · 1 reportApr 26, 2026 · source |
| 3 | DeepSeek-V3.2-BaseDeepSeek | 88.2% | Reported configurationDeepSeek report1 value · 1 reportApr 26, 2026 · source |
Effort curve
Every sourced cost-linked effort value for this exact version. Lines connect complete sweeps only.
No cost-linked effort sweep for this version.
Definition and comparison boundarypublic methodology
Can the model solve difficult problems that require more than factual recall?
Multi-step reasoning on academic, mathematical, or abstract problems. Higher is better. The value is the percentage reported in this lab's table.
Harness, tools, prompts, attempt count, and benchmark version can materially change the result. Compare within one reporting context.
1-shot.
Method / source