Noometry

Model comparison

Magistral Medium vs Nemotron 3 Ultra

Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 35.2 on the Noometry Index.

Last verified . 18 shared benchmarks.

Magistral Medium Mistral AI

35.2

Rank #227 Confirmed

Nemotron 3 Ultra NVIDIA

42.5

Rank #113 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Magistral Medium scores higher in 1 category and Nemotron 3 Ultra in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Nemotron 3 Ultra leads 31.0 to 8.6.
  • Nemotron 3 Ultra is cheaper at $0.60 / $2.40 per million input/output tokens, against $2 / $5 for Magistral Medium.

Side by side

Magistral MediumNemotron 3 Ultra
ProviderMistral AINVIDIA
Noometry Index35.242.5
Released2025-03-172026-06-04
WeightsOpenOpen
Context window262K262K
Max output16K128K
Input $ / M tokens$2$0.60
Output $ / M tokens$5$2.40
Results tracked2230

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Magistral Medium leads

Magistral Medium: 39.1 (#161), Nemotron 3 Ultra: 38.1 (#182)

BenchmarkMagistral MediumNemotron 3 Ultra
SciCode39.2%40.3%
LMArena Coding13191468
FrontierCode—13.6%
WeirdML—43.5%

Agentic & Tool Use Not comparable

Magistral Medium: —, Nemotron 3 Ultra: 23.4 (#126)

BenchmarkMagistral MediumNemotron 3 Ultra
APEX-Agents—22.7%

Reasoning Nemotron 3 Ultra leads

Magistral Medium: 8.6 (#348), Nemotron 3 Ultra: 31.0 (#82)

BenchmarkMagistral MediumNemotron 3 Ultra
CritPt0.3%3.1%
LMArena Hard Prompts12671452
ARC-AGI-20%—
Kagi LLM Benchmark16.2%—
ARC-AGI-16.1%—
Chess Puzzles—12%
Mystery Game Puzzles—20%
DTBench—90.1%
LMCA—36.9%
Epoch Capabilities Index—146.17

Math Too close to call

Magistral Medium: 35.1 (#189), Nemotron 3 Ultra: 35.3 (#187)

BenchmarkMagistral MediumNemotron 3 Ultra
LMArena Math12501457
OTIS Mock AIME 2024-2025—86.7%
ProofBench—2%

Knowledge Nemotron 3 Ultra leads

Magistral Medium: 33.5 (#202), Nemotron 3 Ultra: 52.5 (#61)

BenchmarkMagistral MediumNemotron 3 Ultra
LMArena Expert12231472
GPQA Diamond—85.4%

Multilingual Nemotron 3 Ultra leads

Magistral Medium: 39.6 (#224), Nemotron 3 Ultra: 53.5 (#64)

BenchmarkMagistral MediumNemotron 3 Ultra
LMArena Non-English12321427
LMArena Chinese12271497
LMArena French12671472
LMArena German12481471
LMArena Korean11251386
LMArena Russian12241417
LMArena Spanish12711454
LMArena Japanese1175—

Instruction Following Nemotron 3 Ultra leads

Magistral Medium: 66.0 (#211), Nemotron 3 Ultra: 74.7 (#88)

BenchmarkMagistral MediumNemotron 3 Ultra
LMArena Instruction Following12541418

Long Context Nemotron 3 Ultra leads

Magistral Medium: 39.3 (#183), Nemotron 3 Ultra: 43.9 (#81)

BenchmarkMagistral MediumNemotron 3 Ultra
LMArena Longer Query12951437

Writing & Preference Nemotron 3 Ultra leads

Magistral Medium: 46.3 (#219), Nemotron 3 Ultra: 66.3 (#36)

BenchmarkMagistral MediumNemotron 3 Ultra
LMArena Text12551445
LMArena Creative Writing12451398
LMArena Multi-Turn12751411
EQ-Bench Creative Writing—1692

Frequently asked questions

Is Magistral Medium better than Nemotron 3 Ultra?

Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 35.2 on the Noometry Index.

Which is cheaper, Magistral Medium or Nemotron 3 Ultra?

Nemotron 3 Ultra is cheaper. It lists at $0.60 per million input tokens and $2.40 per million output tokens; Magistral Medium lists at $2 and $5.

Is Magistral Medium or Nemotron 3 Ultra better for coding?

Magistral Medium scores higher on coding benchmarks: 39.1 versus 38.1 in the Noometry coding category.

Which has the bigger context window?

Both accept 262K tokens.

How many benchmarks do Magistral Medium and Nemotron 3 Ultra share?

18 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Nemotron 3 Ultra has 30.

Related comparisons

Go deeper