Head-to-head comparison across 1benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
DeepSeek V3
36
DeepSeek V4 Pro Base
43
Pick DeepSeek V4 Pro Base if you want the stronger benchmark profile. DeepSeek V3 only becomes the better choice if knowledge is the priority.
Knowledge
+6.6 difference
DeepSeek V3
DeepSeek V4 Pro Base
$0.27 / $1.1
$null / $null
N/A
N/A
N/A
N/A
128K
1M
Pick DeepSeek V4 Pro Base if you want the stronger benchmark profile. DeepSeek V3 only becomes the better choice if knowledge is the priority.
DeepSeek V4 Pro Base is clearly ahead on the provisional aggregate, 43 to 36. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
DeepSeek V4 Pro Base gives you the larger context window at 1M, compared with 128K for DeepSeek V3.
DeepSeek V4 Pro Base is ahead on BenchLM's provisional leaderboard, 43 to 36. The biggest single separator in this matchup is MMLU-Pro, where the scores are 75.9% and 73.5%.
DeepSeek V3 has the edge for knowledge tasks in this comparison, averaging 70 versus 63.4. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.
Estimates at 50,000 req/day · 1000 tokens/req average.
For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.