Noometry

Model comparison

Nemotron 3 Ultra vs Qwen2.5-Max

Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 40.7 on the Noometry Index.

Last verified . 17 shared benchmarks.

Nemotron 3 Ultra NVIDIA

42.5

Rank #113 Confirmed

Qwen2.5-Max Alibaba (Qwen)

40.7

Rank #146 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Nemotron 3 Ultra scores higher in 6 categories and Qwen2.5-Max in 2 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 35.3.
  • Nemotron 3 Ultra has downloadable open weights; the other is API-only.

Side by side

Nemotron 3 UltraQwen2.5-Max
ProviderNVIDIAAlibaba (Qwen)
Noometry Index42.540.7
Released2026-06-042025-01-25
WeightsOpenProprietary
Context window262K—
Max output128K—
Input $ / M tokens$0.50—
Output $ / M tokens$2.20—
Results tracked3027

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

Category by category

Coding Qwen2.5-Max leads

Nemotron 3 Ultra: 38.1 (#182), Qwen2.5-Max: 41.8 (#117)

BenchmarkNemotron 3 UltraQwen2.5-Max
LMArena Coding14681359
FrontierCode13.6%—
SciCode40.3%—
WeirdML43.5%—
LiveBench Coding—64.4%

Agentic & Tool Use Not comparable

Nemotron 3 Ultra: 23.4 (#126), Qwen2.5-Max: —

BenchmarkNemotron 3 UltraQwen2.5-Max
APEX-Agents22.7%—

Reasoning Nemotron 3 Ultra leads

Nemotron 3 Ultra: 31.0 (#82), Qwen2.5-Max: 25.6 (#147)

BenchmarkNemotron 3 UltraQwen2.5-Max
LMArena Hard Prompts14521360
Epoch Capabilities Index146.17132.53
CritPt3.1%—
Chess Puzzles12%—
LiveBench Reasoning—51.4%
Mystery Game Puzzles20%—
DTBench90.1%—
LiveBench Data Analysis—67.9%
LMCA36.9%—
LiveBench—62.3%

Math Qwen2.5-Max leads

Nemotron 3 Ultra: 35.3 (#187), Qwen2.5-Max: 36.9 (#162)

BenchmarkNemotron 3 UltraQwen2.5-Max
LMArena Math14571369
OTIS Mock AIME 2024-202586.7%—
ProofBench2%—
LiveBench Math—58.4%

Knowledge Nemotron 3 Ultra leads

Nemotron 3 Ultra: 52.5 (#61), Qwen2.5-Max: 35.3 (#186)

BenchmarkNemotron 3 UltraQwen2.5-Max
LMArena Expert14721337
GPQA Diamond85.4%—
Confabulations—21.8%

Multilingual Nemotron 3 Ultra leads

Nemotron 3 Ultra: 53.5 (#64), Qwen2.5-Max: 48.1 (#146)

BenchmarkNemotron 3 UltraQwen2.5-Max
LMArena Non-English14271352
LMArena Chinese14971382
LMArena French14721396
LMArena German14711350
LMArena Korean13861304
LMArena Russian14171353
LMArena Spanish14541377
LMArena Japanese—1300

Instruction Following Nemotron 3 Ultra leads

Nemotron 3 Ultra: 74.7 (#88), Qwen2.5-Max: 71.3 (#152)

BenchmarkNemotron 3 UltraQwen2.5-Max
LMArena Instruction Following14181335
LiveBench Instruction Following—75.3%

Long Context Nemotron 3 Ultra leads

Nemotron 3 Ultra: 43.9 (#81), Qwen2.5-Max: 41.4 (#142)

BenchmarkNemotron 3 UltraQwen2.5-Max
LMArena Longer Query14371358

Writing & Preference Nemotron 3 Ultra leads

Nemotron 3 Ultra: 66.3 (#36), Qwen2.5-Max: 55.4 (#146)

BenchmarkNemotron 3 UltraQwen2.5-Max
LMArena Text14451367
LMArena Creative Writing13981339
LMArena Multi-Turn14111364
Short-Story Creative Writing—72.9%
EQ-Bench Creative Writing1692—
LiveBench Language—56.3%

Frequently asked questions

Is Nemotron 3 Ultra better than Qwen2.5-Max?

Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 40.7 on the Noometry Index.

Is Nemotron 3 Ultra or Qwen2.5-Max better for coding?

Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 38.1 in the Noometry coding category.

How many benchmarks do Nemotron 3 Ultra and Qwen2.5-Max share?

17 benchmarks have published results for both models. Nemotron 3 Ultra has 30 scored results on Noometry and Qwen2.5-Max has 27.

Related comparisons

Go deeper