Leaderboard bars
2 ranked models · higher is better
View accessible chart data
| Model | Rank | Provider | Score |
|---|---|---|---|
| DeepSeek V4 Pro | #1 | DeepSeek | 45% |
| DeepSeek V4 Flash | #2 | DeepSeek | 23.1% |
Loading benchmark header
Loading benchmark registry
Research · Benchmark profile
A short-answer factuality benchmark designed to measure correctness on fact-seeking questions.
Data verified 15 July 2026 · Methodology 1.2.0
Benchmark score on SimpleQA
DeepSeek V4 Pro leads at 45%, followed by DeepSeek V4 Flash (23.1%).
Visual analysis
Three views of the same sourced leaderboard: model placement, the score curve, and descriptive provider averages. These visuals never alter ranking calculations.
2 ranked models · higher is better
| Model | Rank | Provider | Score |
|---|---|---|---|
| DeepSeek V4 Pro | #1 | DeepSeek | 45% |
| DeepSeek V4 Flash | #2 | DeepSeek | 23.1% |
Shows how quickly scores separate down the field
| Model | Rank | Provider | Score |
|---|---|---|---|
| DeepSeek V4 Pro | #1 | DeepSeek | 45% |
| DeepSeek V4 Flash | #2 | DeepSeek | 23.1% |
Average within the visible cohort · descriptive only
| Provider | Models | Average score |
|---|---|---|
| DeepSeek | 2 | 34.0% |
One best score per model · higher is better
| Rank | Model | Provider | License | Score |
|---|---|---|---|---|
| #1 | DeepSeek V4 Pro deepseek-v4-pro | DeepSeek | open | 45% |
| #2 | DeepSeek V4 Flash deepseek-v4-flash | DeepSeek | open | 23.1% |
About SimpleQA
A short-answer factuality benchmark designed to measure correctness on fact-seeking questions. 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 short-answer factuality benchmark designed to measure correctness on fact-seeking questions.
DeepSeek V4 Pro by DeepSeek currently leads with 45%.
2 models in the LuminaBench cohort have a qualifying score on this benchmark.
Yes. This family is ranking-weighted at 3.5% of its capability category. DeepSeek V4 Pro is overall #50.
Related
Rolling · 22 results · Weighted 3.5%
PaperBenchRolling · 2 results · Weighted 3.5%
Finance Agent v2v2 · 4 results · Not Weighted
BenchLM Knowledge priorbench-align-v5.1 · 33 results · Weighted 1.6%
AA Long Context ReasoningRolling · 96 results · Weighted 1.5%
AA-OmniscienceRolling · 94 results · Weighted 1.5%