DSBench (DeepSeek internal)
DeepSeek V4 Pro 0813 71.1% leads since August 2026 DeepSeek internal coding-agent test sets: full-stack development tasks and hard agentic coding problems. Pass-rate scoring.
Lab-created in-house eval (DeepSeek). Unrelated to the 2024 public DSBench data-science benchmark.
- Made by
- DeepSeek
- Released
- August 2026
- Kind
- Building whole projects
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Code
- Tasks
- Kept private
- Strongest model tested
- DeepSeek V4 Pro 0813 #41 on the capability index
- Last in a launch post
- August 2026
- Last model added
- August 2026
DeepSeek V4 Pro 0813 leads with 71.1% among models released by August 2026
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
The newest model with a score here came out in August 2026, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- Claude Fable 5.2
-
Gemini 4 Carbon - GPT-6 Astra
- Claude Opus 5.5
- and 16 more
- 1 DeepSeek V4 Pro 0813 71.1%
- 2 DeepSeek V4 Flash 0731 68.7%
- 3 DeepSeek-V4-Flash-Vision-Exp 63.6%
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | DeepSeek V4 Pro 0813 | 71.1% | Aug 2026 | Lab model card | |
| 2 | DeepSeek V4 Flash 0731 | 68.7% | Jul 2026 | Lab model card | |
| 3 | DeepSeek-V4-Flash-Vision-Exp | 63.6% | Aug 2026 | Lab model card |
2 models have held number one in labs’ own numbers since its release in August 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Labs’ model cards
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Labs’ model cards
One lab put it in a launch post in the last six months
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Aug 21, 2026 | DeepSeek-V4-Flash-Vision-Exp | 63.6 | DSBench-Hard (in-house) |
| Aug 13, 2026 | DeepSeek V4 Pro 0813 | 67.2 | DSBench-Hard (in-house) |
| Aug 13, 2026 | DeepSeek V4 Pro 0813 | 71.1 | DSBench-FullStack (in-house) |
| Jul 31, 2026 | DeepSeek V4 Flash 0731 | 59.6 | DSBench-Hard (in-house) |
| Jul 31, 2026 | DeepSeek V4 Flash 0731 | 68.7 | DSBench-FullStack (in-house) |
More in Coding
- SWE-bench Verified In use 500 human-validated GitHub issues from 12 Python repos. Agent writes a patch that must pass hidden tests. Claude Opus 4.7 83.5%
- LiveCodeBench v6 In use Competitive programming problems collected after model cutoffs from LeetCode, AtCoder, Codeforces. Scored pass@1 on hidden tests. DeepSeek-V4-Pro 93.5%
- SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Fable 5.2 96.6%
- DeepSWE In use 113 original long-horizon engineering tasks across 91 repos and five languages, written from scratch. Hand-written verifiers accept alternative solutions. GPT-6 Astra 74.1%
- SciCode In use Scientist-curated research coding problems split into subproblems across natural sciences. Code checked against test cases.
Seed2.1 Pro 59.8% - Codeforces rating In use Model solves recent Codeforces contest problems. An Elo-style rating is computed from simulated contest performance. DeepSeek V4.1 Flash 3,471