Chinese-SimpleQA
We show this table for reference; we do not rank on it.
A Chinese short-form factuality benchmark reported by DeepSeek for V4 model evaluations.
Benchmark score on Chinese-SimpleQA — October 29, 2026
We compile the Chinese-SimpleQA rows from provider self-reports. DeepSeek V4 Pro 0813 leads the table at 84.4%, followed by DeepSeek V4 Flash 0731 (78.9%) and DeepSeek V4 Pro (High) (77.7%). We do not use these results to rank models overall.
DeepSeek V4 Pro 0813
DeepSeek
DeepSeek V4 Flash 0731
DeepSeek
DeepSeek V4 Pro (High)
DeepSeek
6 modelsKnowledgeCurrentDisplay onlyUpdated October 29, 2026
Benchmark score table (6 models)
| Rank | Model / configuration | Score | Parameters (B) | Open / closed |
|---|---|---|---|---|
| 1 | DeepSeek V4 Pro 0813DeepSeek | 84.4% | Not reported | Open |
| 2 | DeepSeek V4 Flash 0731DeepSeek | 78.9% | Not reported | Open |
| 3 | DeepSeek V4 Pro (High)DeepSeek | 77.7% | Not reported | Open |
| 4 | DeepSeek V4 ProDeepSeek | 75.8% | Not reported | Open |
| 5 | DeepSeek V4 Flash (High)DeepSeek | 73.2% | Not reported | Open |
| 6 | DeepSeek V4 FlashDeepSeek | 71.5% | Not reported | Open |
Among the reported Chinese-SimpleQA rows, DeepSeek V4 Pro 0813 is first at 84.4%. The third row is 6.7 points behind. The broader top-10 range is 12.9 points, so the table still separates the published systems.
6 models have been evaluated on Chinese-SimpleQA. The benchmark falls in the Knowledge category. Chinese-SimpleQA is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About Chinese-SimpleQA
Year
2026
Tasks
Chinese factual questions
Format
Short-form factual QA
Difficulty
Factual accuracy focused
BenchLM stores Chinese-SimpleQA as a display-only provider-table reference for DeepSeek-V4. It is separate from the English SimpleQA row.
Freshness and provenance
Version
Chinese-SimpleQA 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 Chinese-SimpleQA measure?
A Chinese short-form factuality benchmark reported by DeepSeek for V4 model evaluations.
Which model scores highest on Chinese-SimpleQA?
DeepSeek V4 Pro 0813 by DeepSeek currently leads with a score of 84.4% on Chinese-SimpleQA.
How many models are evaluated on Chinese-SimpleQA?
6 AI models have published results on Chinese-SimpleQA in the BenchLM catalog.
Compare top models on Chinese-SimpleQA
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.