Model comparison
GPT-5.4 Pro vs Nemotron 3 Ultra
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 42.5 on the Noometry Index. Nemotron 3 Ultra costs 73× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.
Last verified . 5 shared benchmarks.
NVIDIASummary
- They share 5 benchmarks with published results for both. GPT-5.4 Pro scores higher in 4 categories and Nemotron 3 Ultra in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.4 Pro leads 70.7 to 31.0.
- The biggest single-benchmark swing is Chess Puzzles: 58.6% for GPT-5.4 Pro and 12% for Nemotron 3 Ultra.
- Nemotron 3 Ultra is cheaper at $0.50 / $2.20 per million input/output tokens, against $30 / $180 for GPT-5.4 Pro.
- GPT-5.4 Pro accepts more context: 1.05M tokens versus 262K.
- Nemotron 3 Ultra has downloadable open weights; the other is API-only.
Side by side
| GPT-5.4 Pro | Nemotron 3 Ultra | |
|---|---|---|
| Provider | OpenAI | NVIDIA |
| Noometry Index | 58.9 | 42.5 |
| Released | 2026-03-05 | 2026-06-04 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 128K | 128K |
| Input $ / M tokens | $30 | $0.50 |
| Output $ / M tokens | $180 | $2.20 |
| Results tracked | 16 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 Pro leads
GPT-5.4 Pro: 43.2 (#90), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | GPT-5.4 Pro | Nemotron 3 Ultra |
|---|---|---|
| WeirdML | 57.4% | 43.5% |
| FrontierCode | — | 13.6% |
| SciCode | — | 40.3% |
| LMArena Coding | — | 1468 |
Agentic & Tool Use Not comparable
GPT-5.4 Pro: —, Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | GPT-5.4 Pro | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | — | 22.7% |
Reasoning GPT-5.4 Pro leads
GPT-5.4 Pro: 70.7 (#13), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | GPT-5.4 Pro | Nemotron 3 Ultra |
|---|---|---|
| CritPt | 30% | 3.1% |
| Chess Puzzles | 58.6% | 12% |
| Epoch Capabilities Index | 158.93 | 146.17 |
| ARC-AGI-2 | 83.3% | — |
| SimpleBench | 74.1% | — |
| ARC-AGI-1 | 94.5% | — |
| EnigmaEval | 23.8% | — |
| LMArena Hard Prompts | — | 1452 |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 90.1% |
| LMCA | — | 36.9% |
Math GPT-5.4 Pro leads
GPT-5.4 Pro: 72.4 (#22), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | GPT-5.4 Pro | Nemotron 3 Ultra |
|---|---|---|
| FrontierMath (Tiers 1-3) | 82.5% | — |
| FrontierMath Tier 4 | 58.5% | — |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| ProofBench | — | 2% |
| LMArena Math | — | 1457 |
| FrontierMath (Feb 2025 set) | 50% | — |
| FrontierMath Tier 4 (v1) | 37.5% | — |
Knowledge GPT-5.4 Pro leads
GPT-5.4 Pro: 68.3 (#7), Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | GPT-5.4 Pro | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | 94.6% | 85.4% |
| Humanity's Last Exam | 44.3% | — |
| SimpleQA Verified | 46.3% | — |
| Vectara Hallucination Rate | 8.3% | — |
| LMArena Expert | — | 1472 |
Multilingual Not comparable
GPT-5.4 Pro: —, Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | GPT-5.4 Pro | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | — | 1427 |
| LMArena Chinese | — | 1497 |
| LMArena French | — | 1472 |
| LMArena German | — | 1471 |
| LMArena Korean | — | 1386 |
| LMArena Russian | — | 1417 |
| LMArena Spanish | — | 1454 |
Instruction Following Not comparable
GPT-5.4 Pro: —, Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | GPT-5.4 Pro | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | — | 1418 |
Long Context Not comparable
GPT-5.4 Pro: —, Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | GPT-5.4 Pro | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | — | 1437 |
Writing & Preference Not comparable
GPT-5.4 Pro: —, Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | GPT-5.4 Pro | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | — | 1445 |
| LMArena Creative Writing | — | 1398 |
| EQ-Bench Creative Writing | — | 1692 |
| LMArena Multi-Turn | — | 1411 |
Frequently asked questions
Is GPT-5.4 Pro better than Nemotron 3 Ultra?
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 42.5 on the Noometry Index. Nemotron 3 Ultra costs 73× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.
Which is cheaper, GPT-5.4 Pro 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; GPT-5.4 Pro lists at $30 and $180.
Is GPT-5.4 Pro or Nemotron 3 Ultra better for coding?
GPT-5.4 Pro scores higher on coding benchmarks: 43.2 versus 38.1 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 Pro does, with 1.05M tokens against 262K.
How many benchmarks do GPT-5.4 Pro and Nemotron 3 Ultra share?
5 benchmarks have published results for both models. GPT-5.4 Pro has 16 scored results on Noometry and Nemotron 3 Ultra has 30.