Model comparison

Nemotron 3 Super vs o3-pro

o3-pro is the stronger model overall, scoring 42.9 to 40.1 on the Noometry Index. Nemotron 3 Super costs 203× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.

Last verified . 1 shared benchmarks.

Nemotron 3 Super NVIDIA

40.1

Rank #153 Confirmed

o3-pro OpenAI

42.9

Rank #105 Confirmed

Summary

  • They share 1 benchmark with published results for both. Nemotron 3 Super scores higher in 1 category and o3-pro in 4 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in long context, where o3-pro leads 72.2 to 41.5.
  • The biggest single-benchmark swing is WeirdML: 38% for Nemotron 3 Super and 58.2% for o3-pro.
  • Nemotron 3 Super is cheaper at $0.08 / $0.45 per million input/output tokens, against $20 / $80 for o3-pro.
  • Nemotron 3 Super accepts more context: 262K tokens versus 200K.
  • Nemotron 3 Super has downloadable open weights; the other is API-only.

Side by side

Nemotron 3 Super and o3-pro specifications
Nemotron 3 Supero3-pro
ProviderNVIDIAOpenAI
Noometry Index40.142.9
Released2026-03-112025-06-10
WeightsOpenProprietary
Context window262K200K
Max output131K100K
Input $ / M tokens$0.08$20
Output $ / M tokens$0.45$80
Results tracked2112

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

Category by category

Coding o3-pro leads

Nemotron 3 Super: 39.4 (#158), o3-pro: 55.5 (#24)

Coding benchmarks
BenchmarkNemotron 3 Supero3-pro
WeirdML38%58.2%
Aider Polyglot—84.9%
SciCode36%—
LMArena Coding1403—
ALE-Bench213.9—

Reasoning o3-pro leads

Nemotron 3 Super: 18.7 (#276), o3-pro: 23.8 (#171)

Reasoning benchmarks
BenchmarkNemotron 3 Supero3-pro
ARC-AGI-2—4.9%
Kagi LLM Benchmark—72.1%
NYT Connections (extended)15.4%—
ARC-AGI-1—59.3%
CritPt3.1%—
LMArena Hard Prompts1386—
DTBench—86.9%
LMCA—38.5%
Epoch Capabilities Index—147.42

Math Not comparable

Nemotron 3 Super: 39.6 (#101), o3-pro: —

Math benchmarks
BenchmarkNemotron 3 Supero3-pro
MathArena Final-Answer Competitions60.4%—
LMArena Math1380—

Knowledge Nemotron 3 Super leads

Nemotron 3 Super: 38.9 (#139), o3-pro: 29.5 (#238)

Knowledge benchmarks
BenchmarkNemotron 3 Supero3-pro
Confabulations—14.2%
Vectara Hallucination Rate—23.3%
LMArena Expert1398—

Multilingual Not comparable

Nemotron 3 Super: 48.4 (#144), o3-pro: —

Multilingual benchmarks
BenchmarkNemotron 3 Supero3-pro
LMArena Non-English1355—
LMArena Chinese1432—
LMArena French1405—
LMArena German1341—
LMArena Russian1336—
LMArena Spanish1417—

Instruction Following Not comparable

Nemotron 3 Super: 71.2 (#154), o3-pro: —

Instruction Following benchmarks
BenchmarkNemotron 3 Supero3-pro
LMArena Instruction Following1347—

Long Context o3-pro leads

Nemotron 3 Super: 41.5 (#139), o3-pro: 72.2 (#1)

Long Context benchmarks
BenchmarkNemotron 3 Supero3-pro
Fiction.LiveBench—97.2%
LMArena Longer Query1362—

Writing & Preference o3-pro leads

Nemotron 3 Super: 55.9 (#140), o3-pro: 57.1 (#133)

Writing & Preference benchmarks
BenchmarkNemotron 3 Supero3-pro
LMArena Text1378—
LMArena Creative Writing1317—
Short-Story Creative Writing—84.4%
LMArena Multi-Turn1369—

Frequently asked questions

Is Nemotron 3 Super better than o3-pro?

o3-pro is the stronger model overall, scoring 42.9 to 40.1 on the Noometry Index. Nemotron 3 Super costs 203× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.

Which is cheaper, Nemotron 3 Super or o3-pro?

Nemotron 3 Super is cheaper. It lists at $0.08 per million input tokens and $0.45 per million output tokens; o3-pro lists at $20 and $80.

Is Nemotron 3 Super or o3-pro better for coding?

o3-pro scores higher on coding benchmarks: 55.5 versus 39.4 in the Noometry coding category.

Which has the bigger context window?

Nemotron 3 Super does, with 262K tokens against 200K.

How many benchmarks do Nemotron 3 Super and o3-pro share?

1 benchmark has published results for both models. Nemotron 3 Super has 21 scored results on Noometry and o3-pro has 12.

Related comparisons

Go deeper