Model comparison
GPT-5.4 Pro vs Nemotron 3 Super
GPT-5.4 Pro is the stronger model overall, scoring 58.8 to 39.6 on the Noometry Index. Nemotron 3 Super costs 391× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
NVIDIASummary
- They share 2 benchmarks with published results for both. GPT-5.4 Pro scores higher in 4 categories and Nemotron 3 Super in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.4 Pro leads 71.0 to 17.9.
- The biggest single-benchmark swing is CritPt: 30% for GPT-5.4 Pro and 3.1% for Nemotron 3 Super.
- Nemotron 3 Super is cheaper at $0.08 / $0.45 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 Super has downloadable open weights; the other is API-only.
Side by side
| GPT-5.4 Pro | Nemotron 3 Super | |
|---|---|---|
| Provider | OpenAI | NVIDIA |
| Noometry Index | 58.8 | 39.6 |
| Released | 2026-03-05 | 2026-03-11 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 128K | 131K |
| Input $ / M tokens | $30 | $0.08 |
| Output $ / M tokens | $180 | $0.45 |
| Results tracked | 16 | 21 |
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: 42.6 (#89), Nemotron 3 Super: 38.9 (#153)
| Benchmark | GPT-5.4 Pro | Nemotron 3 Super |
|---|---|---|
| WeirdML | 57.4% | 38% |
| SciCode | — | 36% |
| LMArena Coding | — | 1403 |
| ALE-Bench | — | 213.9 |
Reasoning GPT-5.4 Pro leads
GPT-5.4 Pro: 71.0 (#10), Nemotron 3 Super: 17.9 (#274)
| Benchmark | GPT-5.4 Pro | Nemotron 3 Super |
|---|---|---|
| CritPt | 30% | 3.1% |
| ARC-AGI-2 | 83.3% | — |
| SimpleBench | 74.1% | — |
| NYT Connections (extended) | — | 15.4% |
| ARC-AGI-1 | 94.5% | — |
| Chess Puzzles | 58.6% | — |
| EnigmaEval | 23.8% | — |
| LMArena Hard Prompts | — | 1386 |
| Epoch Capabilities Index | 159.12 | — |
Math GPT-5.4 Pro leads
GPT-5.4 Pro: 72.0 (#17), Nemotron 3 Super: 37.6 (#95)
| Benchmark | GPT-5.4 Pro | Nemotron 3 Super |
|---|---|---|
| FrontierMath (Tiers 1-3) | 82.5% | — |
| FrontierMath Tier 4 | 58.5% | — |
| MathArena Final-Answer Competitions | — | 60.4% |
| LMArena Math | — | 1381 |
| FrontierMath (Feb 2025 set) | 50% | — |
| FrontierMath Tier 4 (v1) | 37.5% | — |
Knowledge GPT-5.4 Pro leads
GPT-5.4 Pro: 68.3 (#6), Nemotron 3 Super: 38.2 (#136)
| Benchmark | GPT-5.4 Pro | Nemotron 3 Super |
|---|---|---|
| GPQA Diamond | 94.6% | — |
| Humanity's Last Exam | 44.3% | — |
| SimpleQA Verified | 46.3% | — |
| Vectara Hallucination Rate | 8.3% | — |
| LMArena Expert | — | 1397 |
Multilingual Not comparable
GPT-5.4 Pro: —, Nemotron 3 Super: 48.6 (#139)
| Benchmark | GPT-5.4 Pro | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | — | 1356 |
| LMArena Chinese | — | 1430 |
| LMArena French | — | 1404 |
| LMArena German | — | 1341 |
| LMArena Russian | — | 1336 |
| LMArena Spanish | — | 1417 |
Instruction Following Not comparable
GPT-5.4 Pro: —, Nemotron 3 Super: 71.4 (#149)
| Benchmark | GPT-5.4 Pro | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | — | 1347 |
Long Context Not comparable
GPT-5.4 Pro: —, Nemotron 3 Super: 41.5 (#134)
| Benchmark | GPT-5.4 Pro | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | — | 1362 |
Writing & Preference Not comparable
GPT-5.4 Pro: —, Nemotron 3 Super: 56.1 (#135)
| Benchmark | GPT-5.4 Pro | Nemotron 3 Super |
|---|---|---|
| LMArena Text | — | 1378 |
| LMArena Creative Writing | — | 1317 |
| LMArena Multi-Turn | — | 1369 |
Frequently asked questions
Is GPT-5.4 Pro better than Nemotron 3 Super?
GPT-5.4 Pro is the stronger model overall, scoring 58.8 to 39.6 on the Noometry Index. Nemotron 3 Super costs 391× 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 Super?
Nemotron 3 Super is cheaper. It lists at $0.08 per million input tokens and $0.45 per million output tokens; GPT-5.4 Pro lists at $30 and $180.
Is GPT-5.4 Pro or Nemotron 3 Super better for coding?
GPT-5.4 Pro scores higher on coding benchmarks: 42.6 versus 38.9 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 Super share?
2 benchmarks have published results for both models. GPT-5.4 Pro has 16 scored results on Noometry and Nemotron 3 Super has 21.