WinoGrande leaderboard
2 ranked models · higher is better
View accessible chart data
| Model | Rank | Provider | Score |
|---|---|---|---|
| DeepSeek V4 Pro Base | #1 | DeepSeek | 81.5% |
| DeepSeek V4 Flash Base | #2 | DeepSeek | 79.5% |
Loading benchmark header
Loading benchmark registry
Reasoning · Benchmark profile
A commonsense coreference benchmark reported in DeepSeek-V4 base-model evaluations.
Data verified 21 Jul 2026 · Methodology 1.6.0
Benchmark score on WinoGrande
DeepSeek V4 Pro Base leads at 81.5%, followed by DeepSeek V4 Flash Base (79.5%).
Visual analysis
Switch between model placement, score distribution and descriptive provider averages. Every view uses the same sourced leaderboard.
2 ranked models · higher is better
| Model | Rank | Provider | Score |
|---|---|---|---|
| DeepSeek V4 Pro Base | #1 | DeepSeek | 81.5% |
| DeepSeek V4 Flash Base | #2 | DeepSeek | 79.5% |
One best score per model · higher is better
| Rank | Model | Provider | License | Evidence use | Score |
|---|---|---|---|---|---|
| #1 | DeepSeek V4 Pro Base deepseek-v4-pro-base | DeepSeek | open | Estimated reference | 81.5% |
| #2 | DeepSeek V4 Flash Base deepseek-v4-flash-base | DeepSeek | open | Estimated reference | 79.5% |
About WinoGrande
A commonsense coreference benchmark reported in DeepSeek-V4 base-model evaluations. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.
Open benchmark source ↗FAQ
A commonsense coreference benchmark reported in DeepSeek-V4 base-model evaluations.
DeepSeek V4 Pro Base by DeepSeek currently leads with 81.5%.
2 models in the LuminaBench cohort have a qualifying score on this benchmark.
Related