Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

Gemma 4 31B vs Nemotron 3 Ultra 550B A55B

Google · released

Wins 0 of 7 areas

—

NVIDIA · released

Wins 7 of 7 areas

Coding · Agents · Reasoning · Facts · Math · Long documents · Following instructions

Nemotron 3 Ultra 550B A55B is the stronger all-rounder.Gemma 4 31B is cheaper.

Scores updated · 35 tests both models report · How we compare

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.

Gemma 4 31B$0.15 to read · $0.40 to write$0.55Price from Artificial Analysis
Nemotron 3 Ultra 550B A55B$0.55 to read · $2.30 to write$2.85Price from Artificial Analysis

Gemma 4 31B costs 81% less for the same work.

The biggest differences

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

Where Nemotron 3 Ultra 550B A55B pulls ahead

  • Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+55.3points aheadNemotron 3 Ultra 550B A55B70.3Gemma 4 31B15
  • Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+24.7points aheadNemotron 3 Ultra 550B A55B67.7Gemma 4 31B43
  • Fixes real GitHub issues in Python projectsSWE-bench Verified+24.6points aheadNemotron 3 Ultra 550B A55B70.7Gemma 4 31B46.1

Where Gemma 4 31B pulls ahead

  • Multi-step tasks using many real software toolsMCP Atlas+9.5points aheadGemma 4 31B54.2Nemotron 3 Ultra 550B A55B44.7
  • Code for real scientific research problemsSciCode+5.2points aheadGemma 4 31B45.5Nemotron 3 Ultra 550B A55B40.3

Every test, side by side

All 35 tests both models report. The winning score is in its model's colour; marks a score checked independently.

CodingNemotron 3 Ultra 550B A55B

Full coding ranking

AgentsNemotron 3 Ultra 550B A55B

Full agents ranking

ReasoningNemotron 3 Ultra 550B A55B

Full reasoning ranking

FactsNemotron 3 Ultra 550B A55B

Full facts ranking

MathNemotron 3 Ultra 550B A55B

Full math ranking

Long documentsNemotron 3 Ultra 550B A55B
  • AA-LCRNemotron 3 Ultra 550B A55B by 9.669.779.3+9.6
  • LongBench v2Nemotron 3 Ultra 550B A55B by 952.961.9+9

Full long documents ranking

Following instructionsNemotron 3 Ultra 550B A55B
  • IFBenchNemotron 3 Ultra 550B A55B by 5.875.681.4+5.8

Full following instructions ranking

Other results11 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, Gemma 4 31B or Nemotron 3 Ultra 550B A55B?

Nemotron 3 Ultra 550B A55B wins all seven areas where both have results: coding, agents, reasoning, facts, math, long documents and following instructions. Gemma 4 31B wins none, but costs 81% less.

Which is better for coding?

Nemotron 3 Ultra 550B A55B. It wins 5 of the 7 coding tests both models report; Gemma 4 31B wins 1, and 1 is a tie.

Which is cheaper?

Gemma 4 31B costs $0.15 per million input tokens and $0.40 per million output tokens; Nemotron 3 Ultra 550B A55B costs $0.55 and $2.30. That makes Gemma 4 31B about 81% cheaper for the same work.

How do you compare the two?

We use the 35 benchmark tests both models have published scores on. The verdict counts the 24 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 11 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.