Noometry

Model comparison

Claude Sonnet 4.5 vs Nemotron 3 Ultra

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 42.5 on the Noometry Index. Nemotron 3 Ultra costs 6.5× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

Last verified . 28 shared benchmarks.

Claude Sonnet 4.5 Anthropic

44.1

Rank #81 Confirmed

Nemotron 3 Ultra NVIDIA

42.5

Rank #113 Confirmed

Summary

  • They share 28 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 5 categories and Nemotron 3 Ultra in 4 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in agentic & tool use, where Claude Sonnet 4.5 leads 38.3 to 23.4.
  • The biggest single-benchmark swing is ProofBench: 19% for Claude Sonnet 4.5 and 2% for Nemotron 3 Ultra.
  • Nemotron 3 Ultra is cheaper at $0.50 / $2.20 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
  • Nemotron 3 Ultra accepts more context: 262K tokens versus 200K.
  • Nemotron 3 Ultra has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 4.5Nemotron 3 Ultra
ProviderAnthropicNVIDIA
Noometry Index44.142.5
Released2025-09-292026-06-04
WeightsProprietaryOpen
Context window200K262K
Max output64K128K
Input $ / M tokens$3$0.50
Output $ / M tokens$15$2.20
Results tracked7330

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

Category by category

Coding Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 47.3 (#61), Nemotron 3 Ultra: 38.1 (#182)

BenchmarkClaude Sonnet 4.5Nemotron 3 Ultra
SciCode44.7%40.3%
WeirdML47.7%43.5%
LMArena Coding14891468
SWE-bench Verified71.3%—
FrontierCode—13.6%
SWE-bench Verified (bash only)71.4%—
LMArena WebDev1393—
SWE-bench Multilingual67%—
GSO14.7%—
ALE-Bench796.15—
AlgoTune1.52—

Agentic & Tool Use Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 38.3 (#32), Nemotron 3 Ultra: 23.4 (#126)

BenchmarkClaude Sonnet 4.5Nemotron 3 Ultra
Terminal-Bench46.5%—
APEX-Agents—22.7%
Berkeley Function Calling Leaderboard73.2%—
GDPval42.5%—
Remote Labor Index2.1%—
τ²-bench Airline72%—
τ²-bench Banking25.3%—
τ²-bench Retail72.4%—
τ²-bench Telecom84.9%—
Cybench60%—
DeepResearch Bench52.6%—
OSWorld62.9%—
LMArena Search1159—
METR Time Horizons67.4%—
Vending-Bench 23,839—

Reasoning Nemotron 3 Ultra leads

Claude Sonnet 4.5: 26.9 (#125), Nemotron 3 Ultra: 31.0 (#82)

BenchmarkClaude Sonnet 4.5Nemotron 3 Ultra
CritPt1.1%3.1%
Chess Puzzles12%12%
LMArena Hard Prompts14621452
Mystery Game Puzzles17%20%
DTBench83.2%90.1%
LMCA38.8%36.9%
Epoch Capabilities Index146.84146.17
ARC-AGI-213.6%—
SimpleBench54.3%—
Kagi LLM Benchmark57.9%—
NYT Connections (extended)37.3%—
ARC-AGI-163.7%—
EnigmaEval6%—
EBR-Bench2.4%—
ForecastBench61.9—

Math Nemotron 3 Ultra leads

Claude Sonnet 4.5: 32.3 (#216), Nemotron 3 Ultra: 35.3 (#187)

BenchmarkClaude Sonnet 4.5Nemotron 3 Ultra
OTIS Mock AIME 2024-202577.8%86.7%
ProofBench19%2%
LMArena Math14491457
FrontierMath (Tiers 1-3)23.9%—
FrontierMath Tier 42.4%—
Omni-MATH55.3%—
MATH Level 597.7%—
FrontierMath (Feb 2025 set)15.2%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Nemotron 3 Ultra leads

Claude Sonnet 4.5: 48.4 (#76), Nemotron 3 Ultra: 52.5 (#61)

BenchmarkClaude Sonnet 4.5Nemotron 3 Ultra
GPQA Diamond82.3%85.4%
LMArena Expert14821472
Humanity's Last Exam13.7%—
SimpleQA Verified30.7%—
MMLU-Pro86.9%—
Vectara Hallucination Rate12%—
GPQA (HELM)68.6%—

Multimodal Not comparable

Claude Sonnet 4.5: 34.8 (#89), Nemotron 3 Ultra: —

BenchmarkClaude Sonnet 4.5Nemotron 3 Ultra
VPCT39.8%—
LMArena Document1450—

Multilingual Too close to call

Claude Sonnet 4.5: 53.4 (#69), Nemotron 3 Ultra: 53.5 (#64)

BenchmarkClaude Sonnet 4.5Nemotron 3 Ultra
LMArena Non-English14251427
LMArena Chinese14591497
LMArena French14581472
LMArena German14271471
LMArena Korean14031386
LMArena Russian14371417
LMArena Spanish14571454
LMArena Japanese1390—

Instruction Following Too close to call

Claude Sonnet 4.5: 75.0 (#78), Nemotron 3 Ultra: 74.7 (#88)

BenchmarkClaude Sonnet 4.5Nemotron 3 Ultra
LMArena Instruction Following14591418
IFEval85%—

Long Context Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 45.2 (#46), Nemotron 3 Ultra: 43.9 (#81)

BenchmarkClaude Sonnet 4.5Nemotron 3 Ultra
LMArena Longer Query14761437

Writing & Preference Too close to call

Claude Sonnet 4.5: 66.5 (#34), Nemotron 3 Ultra: 66.3 (#36)

BenchmarkClaude Sonnet 4.5Nemotron 3 Ultra
LMArena Text14391445
LMArena Creative Writing14421398
EQ-Bench Creative Writing16781692
LMArena Multi-Turn14651411
WildBench85.4%—

Frequently asked questions

Is Claude Sonnet 4.5 better than Nemotron 3 Ultra?

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 42.5 on the Noometry Index. Nemotron 3 Ultra costs 6.5× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

Which is cheaper, Claude Sonnet 4.5 or Nemotron 3 Ultra?

Nemotron 3 Ultra is cheaper. It lists at $0.50 per million input tokens and $2.20 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.

Is Claude Sonnet 4.5 or Nemotron 3 Ultra better for coding?

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 38.1 in the Noometry coding category.

Which has the bigger context window?

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

How many benchmarks do Claude Sonnet 4.5 and Nemotron 3 Ultra share?

28 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Nemotron 3 Ultra has 30.

Related comparisons

Go deeper