DeepSeek DSBench FullStack (DSBench-FullStack)
We show this table for reference; we do not rank on it.
DeepSeek's internal full-stack coding-agent benchmark.
Benchmark score on DSBench-FullStack — November 13, 2026
We compile the DSBench-FullStack rows from provider self-reports. DeepSeek V4 Pro 0813 leads the table at 71.1%, followed by DeepSeek V4 Flash 0731 (68.7%). We do not use these results to rank models overall.
DeepSeek V4 Pro 0813
DeepSeek
Reported by DeepSeekDeepSeek V4 Flash 0731
DeepSeek
Reported by DeepSeek2 modelsCodingCurrentDisplay onlyUpdated November 13, 2026
Benchmark score table (2 models)
All 2 results on this page were reported by the labs that built the models.
| Rank | Model / configuration | Score | Who ran it | Parameters (B) | Open / closed |
|---|---|---|---|---|---|
| 1 | DeepSeek V4 Pro 0813DeepSeekReported by DeepSeek | 71.1% | Reported by DeepSeek | Not reported | Open |
| 2 | DeepSeek V4 Flash 0731DeepSeekReported by DeepSeek | 68.7% | Reported by DeepSeek | Not reported | Open |
- Lab-reported
- Benchmark-run
- Independent
About DSBench-FullStack
Year
2026
Tasks
Internal full-stack coding-agent tasks
Format
Provider-reported score
Difficulty
Full-stack software engineering
DeepSeek labels DSBench-FullStack as an internal benchmark. BenchLM stores the provider-reported exact result as display-only launch evidence and does not compare it with public benchmark leaderboards.
Freshness and provenance
Version
DSBench-FullStack 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 DSBench-FullStack measure?
DeepSeek's internal full-stack coding-agent benchmark.
Which model scores highest on DSBench-FullStack?
DeepSeek V4 Pro 0813 by DeepSeek currently leads with a score of 71.1% on DSBench-FullStack.
How many models are evaluated on DSBench-FullStack?
2 AI models have published results on DSBench-FullStack in the BenchLM catalog.
Compare top models on DSBench-FullStack
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 7,000+ subscribers.
One email each week. Unsubscribe anytime.