DeepSeek-V4-Pro is the stronger all-rounder.
Scores updated · 10 tests both models report · How we compare
Where each one wins
Tests won in each of the three areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
Agents and reasoning rest on a single test each.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where DeepSeek-V4-Pro pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+69.7points ahead
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+62.1points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+55.7points ahead
Where Nemotron 3 Nano pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 10 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V4-Pro
- SWE-bench MultilingualDeepSeek-V4-Pro by 62.176.214.1+62.1
- Terminal-Bench 2.1DeepSeek-V4-Pro by 55.7648.3+55.7
- SWE-bench VerifiedDeepSeek-V4-Pro by 46.580.634.1+46.5
- SciCodeDeepSeek-V4-Pro by 20.750.830.1+20.7
Other results4 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- GDPval-AA v2DeepSeek-V4-Pro by 833 rating points1306473+833 rating
- PinchBenchDeepSeek-V4-Pro by 22.588.666.1+22.5
- τ³-Bench BankingDeepSeek-V4-Pro by 19267+19
- MMLU-ProDeepSeek-V4-Pro by 987.578.5+9
Questions people ask
Which is better, DeepSeek-V4-Pro or Nemotron 3 Nano?
DeepSeek-V4-Pro wins all three areas where both have results: coding, agents and reasoning. Nemotron 3 Nano wins none.
Which is better for coding?
DeepSeek-V4-Pro. It wins 4 of the 4 coding tests both models report; Nemotron 3 Nano wins none.
How do you compare the two?
We use the 10 benchmark tests both models have published scores on. The verdict counts the 6 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 4 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.