specs at a glance
| Leaderboard rank | #20 of 28 |
|---|---|
| SWE-bench Verified | 80.6% |
| SWE-bench Pro | 55.4% |
| Terminal-Bench | 67.9% (TB2.0) |
| Input price / 1M | $0.435 |
| Output price / 1M | $0.87 |
| Context window | 1M |
| Open weights | Yes |
| Access | Open weights (MIT) · API · self-host |
| Maker | DeepSeek |
how good is DeepSeek V4 Pro at coding?
DeepSeek V4 Pro sits at #20 of 28 ranked models, posting 80.6% on SWE-bench Verified — 16.4 points behind #1 Claude Opus 5. On the harder SWE-bench Pro it scores 55.4%. Terminal-Bench (agentic terminal work): 67.9% (TB2.0).
Score provenance: Vendor-reported: DeepSeek's own model card, Pro-Max mode (SWE-bench Verified 80.6%, SWE-bench Pro 55.4%). Updated Aug 12, 2026: DeepSeek shipped the GA build, DeepSeek-V4-Pro-0813, and repointed the deepseek-v4-pro API alias to it. The published benchmark table did not change, so the ranked score is unmoved; the source link was upgraded from an llm-stats-derived aggregator page to DeepSeek's primary model card. Corrected Jul 17, 2026: we previously called llm-stats an "independent tracker", but llm-stats labels its own SWE-bench Verified table "Verified: 0 / Self-reported: 104", so every score on it is vendor-claimed rather than independent. **An independent score now exists, and it inverts this row, 2026-08-13.** vals.ai has evaluated DeepSeek V4 Pro 0813 at 96.40% ±0.83 on the mini-swe-agent bash-only harness, placing it 2nd of 82 systems, 0.6 points off Claude Opus 5. That is the same GA build this row already documents above (DeepSeek repointed the deepseek-v4-pro API alias to 0813 on Aug 12), so it is an exact match, not a near-miss. It is also 15.8 points ABOVE DeepSeek's own 80.6% claim, which is the opposite direction from every other disclosure row on this board, where vendors run 2.6 to 11.6 points high. We have NOT rebased the ranked score, because this board's standing decision is DISCLOSE, DON'T REBASE: where a vendor figure and an exact independent figure both exist, the maker's number stays ranked and the independent one is disclosed here. That rule was written for vendor overstatement and does not obviously fit a vendor understating its own model by 15.8 points, so this row is flagged for a human decision on whether to rebase it to 96.40% (which would move it from 16th to 2nd and make it the highest-scoring open-weight model on the board). Until that call is made, the ranked score stays at the vendor's 80.6% and readers get the independent number here. vals.ai has also evaluated the plain DeepSeek V4 (77.4%), a different model, and DeepSeek's own smaller V4 Flash 0731 at 88.8%. Tied with Gemini 3.1 Pro on Verified, ahead on Pro. See /p/deepseek-v4-pro-ga-flash-still-scores-higher/.
what does DeepSeek V4 Pro cost?
$0.435 per 1M input tokens and $0.87 per 1M output — #4 cheapest of the 26 models we track. Coding workloads are output-heavy, so weight the output rate when budgeting. Run your own volume through the AI API cost calculator for a monthly estimate.
where can you use it?
Available via Open weights (MIT) · API · self-host. Because it ships open weights, you can also self-host it on your own hardware or any inference provider — with the version pinned so the model can't change under you.
Full storyDeepSeek V4 Pro hits GA, but Flash still scores higher
Ranked on our AI Coding Leaderboard — scores confirmed against primary sources only, updated 2026-08-20.