AI Rankings

DeepSeek V4 Pro

MIT-licensed open-weight heavyweight, among the open-weight leaders on SWE-bench Verified and LiveCodeBench.

Visit official site (opens in a new tab)Compare with another model

Our editorial assessment, based on the public sources listed below. Last reviewed .

Overall rank
#30
Tier
A
Score
83.0
Main category
Coding

Strengths

  • Among the open-weight coding leaders on SWE-bench Verified
  • Top-tier LiveCodeBench results within the open field
  • Fully open MIT weights, unrestricted for fine-tuning

Considerations

  • Trillion-parameter scale is demanding to self-host
  • General chat polish trails the top proprietary flagships
  • DeepSeek says its newer V4.1-Flash already beats V4-Pro on performance, cost and speed, with a V4.1-Pro still to come

Price

API $1.32 input / $3.96 output per 1M tokens at peak hours ($0.66 / $1.98 off-peak); MIT open weights

Shown for reference — price is not part of the score.

Score breakdown

Performance
85.0
55% of score
Reputation
80.0
35% of score
Recency
82.0
10% of score

The overall score combines these sub-scores using the weights shown. How we score →

Verification status

Each field carries its own re-verification date. Amber means older than 90 days — treat those figures as stale until re-checked.

Pricing
Benchmark
source ↗
Reputation
source ↗
Feature list

Checked against the sources listed below.

Sources

Show 15 more sources

Similar models