Discrete Reasoning Over Paragraphs (DROP)
We show this table for reference; we do not rank on it.
A reading-comprehension benchmark requiring discrete reasoning over paragraphs, reported in DeepSeek-V4 base-model evaluations.
Benchmark score on DROP — October 29, 2026
We compile the DROP rows from provider self-reports. DeepSeek V4 Pro Base leads the table at 88.7%, followed by DeepSeek V4 Flash Base (88.6%) and o1-mini (83.9%). We do not use these results to rank models overall.
DeepSeek V4 Pro Base
DeepSeek
DeepSeek V4 Flash Base
DeepSeek
o1-mini
OpenAI
8 modelsReasoningCurrentDisplay onlyUpdated October 29, 2026
Benchmark score table (8 models)
| Rank | Model / configuration | Score | Parameters (B) | Open / closed |
|---|---|---|---|---|
| 1 | DeepSeek V4 Pro BaseDeepSeek | 88.7% | Not reported | Open |
| 2 | DeepSeek V4 Flash BaseDeepSeek | 88.6% | Not reported | Open |
| 3 | o1-miniOpenAI | 83.9% | Not reported | Closed |
| 4 | GPT-4.5OpenAI | 83.4% | Not reported | Closed |
| 5 | Claude 3.5 HaikuAnthropic | 83.1% | Not reported | Closed |
| 6 | Celeris-1Celeris | 81.4% | Not reported | Closed |
| 7 | o4-miniOpenAI | 77.7% | Not reported | Closed |
| 8 | Soofi S 30B-A3BSoofi Project | 66.5% | Not reported | Open |
Among the reported DROP rows, DeepSeek V4 Pro Base is first at 88.7%. The third row is 4.8 points behind. The broader top-10 range is 22.2 points, so the table still separates the published systems.
8 models have been evaluated on DROP. The benchmark falls in the Reasoning category. DROP is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About DROP
Year
2026
Tasks
Paragraph reasoning questions
Format
F1
Difficulty
Reading and numerical reasoning
BenchLM stores DROP as a display-only provider-table row when exact values are published in DeepSeek-V4 evaluations.
Freshness and provenance
Version
DROP 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does DROP measure?
A reading-comprehension benchmark requiring discrete reasoning over paragraphs, reported in DeepSeek-V4 base-model evaluations.
Which model scores highest on DROP?
DeepSeek V4 Pro Base by DeepSeek currently leads with a score of 88.7% on DROP.
How many models are evaluated on DROP?
8 AI models have published results on DROP in the BenchLM catalog.
Compare top models on DROP
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 6,100+ subscribers.
One email each week. Unsubscribe anytime.