The Model Index
Up to four models

GPT-5.4 Nano vs Nemotron 3 Ultra

On the index (GPT-4 = 100), GPT-5.4 Nano scores 141 and Nemotron 3 Ultra 141. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to GPT-5.4 Nano
Presets
GPT-5.4 Nano
141125–157
WeightsClosed
ReleasedMar 2026
Price in / out$0.20 / $1.25
Context400K
Core tests taken4 of 9
Nemotron 3 Ultra
141124–157
WeightsOpen
ReleasedJun 2026
Price in / out$0.50 / $2.2
Context262K
Core tests taken3 of 9

GPT-5.4 Nano and Nemotron 3 Ultra are too close to call (1 point apart, within the uncertainty), ahead on 1 of 2 shared core tests, and costs 2.0× less.

Test by testthird-party results

GPT-5.4 NanoNemotron 3 Ultra
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)GPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)CODINGCode MigrationCode MigrationLiveCodeBenchLiveCodeBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1WeirdMLWeirdMLAGENTSDTBenchDTBenchLMCALMCAMystery game puzzlesMystery game puzzlesPROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)CorpFin v2CorpFin v2EMBEMBLegalBenchLegalBenchLegal Research BenchLegal Research BenchMedCodeMedCodeTaxEval v2TaxEval v2
Every result as a table
TestGPT-5.4 NanoNemotron 3 Ultra
Reasoning & knowledge
GPQA Diamond (Epoch AI)78.5%85.4%
GPQA Diamond (Vals AI)77.5%86.1%
MMLU Pro77.2%85.8%
Maths
AIME-style maths (OTIS mock)87.8%86.7%
Coding
Code Migration14.5%4.9%
LiveCodeBench84.0%86.0%
SWE-bench69.8%69.0%
Vibe Code Bench v1.126.1%7.6%
WeirdML49.2%43.5%
Agents
DTBench80.3%90.1%
LMCA36.9%36.9%
Mystery game puzzles9.0%20.0%
Professional work
Finance Agent (v2)38.2%37.7%
CorpFin v261.2%65.5%
EMB44.8%31.7%
LegalBench77.9%82.1%
Legal Research Bench6.3%15.4%
MedCode41.0%38.6%
TaxEval v267.4%73.1%

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG