Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d272Policy30d66, 14 pendingSources1,015

DeepSeek-V3.1-Terminus vs Nemotron 3 Super 120B A12B

DeepSeek · released

Wins 4 of 6 areas

Coding · Agents · Facts · Long documents

NVIDIA · released

Wins 2 of 6 areas

Reasoning · Following instructions

DeepSeek-V3.1-Terminus is the stronger all-rounder.Nemotron 3 Super 120B A12B is cheaper and better at reasoning.

Scores updated · 21 tests both models report · How we compare

Where each one wins

Tests won in each of the six 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.

Long documents rests on a single test.

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.

DeepSeek-V3.1-Terminus$0.27 to read · $1.00 to write$1.27Price from Artificial Analysis
Nemotron 3 Super 120B A12B$0.30 to read · $0.90 to write$1.20Price from Artificial Analysis

Nemotron 3 Super 120B A12B costs 6% less for the same work.

The biggest differences

The three tests each model wins by the widest margin. Scores are out of 100.

Where DeepSeek-V3.1-Terminus pulls ahead

  • Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+12.2points aheadDeepSeek-V3.1-Terminus25.2Nemotron 3 Super 120B A12B13
  • Customer-service tasks in a simulated bankτ-Bench V3 · Banking+10.7points aheadDeepSeek-V3.1-Terminus21Nemotron 3 Super 120B A12B10.3
  • Command-line tasks in a real terminalTerminal-Bench 2.1+6.3points aheadDeepSeek-V3.1-Terminus44.9Nemotron 3 Super 120B A12B38.6

Where Nemotron 3 Super 120B A12B pulls ahead

  • Follows unfamiliar, precisely checkable instructionsIFBench+14.5points aheadNemotron 3 Super 120B A12B71.5DeepSeek-V3.1-Terminus57
  • Very hard expert questions across many subjectsHumanity's Last Exam+4.4points aheadNemotron 3 Super 120B A12B20.8DeepSeek-V3.1-Terminus16.4
  • Research-level physics problemsCritPt+1.4points aheadNemotron 3 Super 120B A12B3.1DeepSeek-V3.1-Terminus1.7

Every test, side by side

All 21 tests both models report. The winning score is in its model's colour; marks a score checked independently.

CodingDeepSeek-V3.1-Terminus

Full coding ranking

AgentsDeepSeek-V3.1-Terminus

Full agents ranking

ReasoningNemotron 3 Super 120B A12B

Full reasoning ranking

FactsDeepSeek-V3.1-Terminus

Full facts ranking

Long documentsDeepSeek-V3.1-Terminus
  • AA-LCRDeepSeek-V3.1-Terminus by 3.669.365.7+3.6

Full long documents ranking

Following instructionsNemotron 3 Super 120B A12B

Full following instructions ranking

Other results7 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.

Questions people ask

Which is better, DeepSeek-V3.1-Terminus or Nemotron 3 Super 120B A12B?

DeepSeek-V3.1-Terminus wins four of the six areas where both have results: coding, agents, facts and long documents. Nemotron 3 Super 120B A12B wins reasoning and following instructions, and costs 6% less.

Which is better for coding?

DeepSeek-V3.1-Terminus. It wins 3 of the 3 coding tests both models report; Nemotron 3 Super 120B A12B wins none.

Which is cheaper?

DeepSeek-V3.1-Terminus costs $0.27 per million input tokens and $1.00 per million output tokens; Nemotron 3 Super 120B A12B costs $0.30 and $0.90. That makes Nemotron 3 Super 120B A12B about 6% cheaper for the same work.

How do you compare the two?

We use the 21 benchmark tests both models have published scores on. The verdict counts the 14 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 7 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.