specs at a glance

Leaderboard rank#8 of 13
SWE-bench Verified80.6%
SWE-bench Pro55.4%
Terminal-Bench67.9% (TB2.0)
Input price / 1M$0.435
Output price / 1M$0.87
Context window1M
Open weightsYes
AccessOpen weights (MIT) · API · self-host
MakerDeepSeek

how good is DeepSeek V4 Pro at coding?

DeepSeek V4 Pro sits at #8 of 13 ranked models, posting 80.6% on SWE-bench Verified — 15.6 points behind #1 GPT-5.6 Sol. On the harder SWE-bench Pro it scores 55.4%. Terminal-Bench (agentic terminal work): 67.9% (TB2.0).

Score provenance: Vendor-reported, as aggregated by llm-stats (June 2026). 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" — every score on it is vendor-claimed, so this is a vendor number, not an independent one. No independent evaluator has run V4 Pro; vals.ai has evaluated the plain DeepSeek V4 (77.4%), which is a different model. Tied with Gemini 3.1 Pro on Verified, ahead on Pro.

what does DeepSeek V4 Pro cost?

$0.435 per 1M input tokens and $0.87 per 1M output — the cheapest model 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.

Ranked on our AI Coding Leaderboard — scores confirmed against primary sources only, updated 2026-07-17.