WinoGrande
We show this table for reference; we do not rank on it.
A commonsense coreference benchmark reported in DeepSeek-V4 base-model evaluations.
Benchmark score on WinoGrande — October 29, 2026
We compile the WinoGrande rows from provider self-reports. DeepSeek V4 Pro Base leads the table at 81.5%, followed by DeepSeek V4 Flash Base (79.5%). We do not use these results to rank models overall.
DeepSeek V4 Pro Base
DeepSeek
DeepSeek V4 Flash Base
DeepSeek
2 modelsReasoningCurrentDisplay onlyUpdated October 29, 2026
Benchmark score table (2 models)
| Rank | Model / configuration | Score | Parameters (B) | Open / closed |
|---|---|---|---|---|
| 1 | DeepSeek V4 Pro BaseDeepSeek | 81.5% | Not reported | Open |
| 2 | DeepSeek V4 Flash BaseDeepSeek | 79.5% | Not reported | Open |
About WinoGrande
Year
2026
Tasks
Coreference resolution questions
Format
Exact match
Difficulty
Commonsense reasoning
BenchLM stores WinoGrande as a display-only provider-table row when exact values are published in DeepSeek-V4 evaluations.
Freshness and provenance
Version
WinoGrande 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 WinoGrande measure?
A commonsense coreference benchmark reported in DeepSeek-V4 base-model evaluations.
Which model scores highest on WinoGrande?
DeepSeek V4 Pro Base by DeepSeek currently leads with a score of 81.5% on WinoGrande.
How many models are evaluated on WinoGrande?
2 AI models have published results on WinoGrande in the BenchLM catalog.
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.