Model comparison
GPT-4 Turbo vs Nemotron 3 Super
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 30.5 on the Noometry Index.
Last verified . 16 shared benchmarks.
NVIDIASummary
- They share 16 benchmarks with published results for both. GPT-4 Turbo scores higher in 0 categories and Nemotron 3 Super in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Nemotron 3 Super leads 39.6 to 9.0.
- The biggest single-benchmark swing is WeirdML: 18% for GPT-4 Turbo and 38% for Nemotron 3 Super.
- Nemotron 3 Super is cheaper at $0.08 / $0.45 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
- Nemotron 3 Super accepts more context: 262K tokens versus 128K.
- Nemotron 3 Super has downloadable open weights; the other is API-only.
Side by side
| GPT-4 Turbo | Nemotron 3 Super | |
|---|---|---|
| Provider | OpenAI | NVIDIA |
| Noometry Index | 30.5 | 40.1 |
| Released | 2023-11-06 | 2026-03-11 |
| Weights | Proprietary | Open |
| Context window | 128K | 262K |
| Max output | 4K | 131K |
| Input $ / M tokens | $10 | $0.08 |
| Output $ / M tokens | $30 | $0.45 |
| Results tracked | 36 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Super leads
GPT-4 Turbo: 33.8 (#249), Nemotron 3 Super: 39.4 (#158)
| Benchmark | GPT-4 Turbo | Nemotron 3 Super |
|---|---|---|
| WeirdML | 18% | 38% |
| LMArena Coding | 1268 | 1403 |
| SciCode | — | 36% |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 58.2% | — |
| ALE-Bench | — | 213.9 |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Not comparable
GPT-4 Turbo: —, Nemotron 3 Super: —
| Benchmark | GPT-4 Turbo | Nemotron 3 Super |
|---|---|---|
| METR Time Horizons | 36.7% | — |
Reasoning Nemotron 3 Super leads
GPT-4 Turbo: 15.3 (#317), Nemotron 3 Super: 18.7 (#276)
| Benchmark | GPT-4 Turbo | Nemotron 3 Super |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1386 |
| SimpleBench | 25.1% | — |
| NYT Connections (extended) | — | 15.4% |
| CritPt | — | 3.1% |
| Chess Puzzles | 6% | — |
| DTBench | 61.6% | — |
| LMCA | 9.8% | — |
| Epoch Capabilities Index | 127.25 | — |
| ForecastBench | 59.4 | — |
Math Nemotron 3 Super leads
GPT-4 Turbo: 9.0 (#322), Nemotron 3 Super: 39.6 (#101)
| Benchmark | GPT-4 Turbo | Nemotron 3 Super |
|---|---|---|
| LMArena Math | 1272 | 1380 |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| MathArena Final-Answer Competitions | — | 60.4% |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
| MATH Level 5 | 46.7% | — |
Knowledge Nemotron 3 Super leads
GPT-4 Turbo: 24.3 (#268), Nemotron 3 Super: 38.9 (#139)
| Benchmark | GPT-4 Turbo | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | 1223 | 1398 |
| GPQA Diamond | 46.6% | — |
| Confabulations | 28.4% | — |
| MMLU | 81.3% | — |
Multimodal Not comparable
GPT-4 Turbo: 30.6 (#110), Nemotron 3 Super: —
| Benchmark | GPT-4 Turbo | Nemotron 3 Super |
|---|---|---|
| LMArena Vision | 1090 | — |
Multilingual Nemotron 3 Super leads
GPT-4 Turbo: 40.5 (#216), Nemotron 3 Super: 48.4 (#144)
| Benchmark | GPT-4 Turbo | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1245 | 1355 |
| LMArena Chinese | 1242 | 1432 |
| LMArena French | 1276 | 1405 |
| LMArena German | 1259 | 1341 |
| LMArena Russian | 1259 | 1336 |
| LMArena Spanish | 1260 | 1417 |
| LMArena Japanese | 1194 | — |
| LMArena Korean | 1187 | — |
Instruction Following Nemotron 3 Super leads
GPT-4 Turbo: 65.8 (#216), Nemotron 3 Super: 71.2 (#154)
| Benchmark | GPT-4 Turbo | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1249 | 1347 |
Long Context Nemotron 3 Super leads
GPT-4 Turbo: 38.0 (#206), Nemotron 3 Super: 41.5 (#139)
| Benchmark | GPT-4 Turbo | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1254 | 1362 |
Writing & Preference Nemotron 3 Super leads
GPT-4 Turbo: 47.7 (#206), Nemotron 3 Super: 55.9 (#140)
| Benchmark | GPT-4 Turbo | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1272 | 1378 |
| LMArena Creative Writing | 1269 | 1317 |
| LMArena Multi-Turn | 1267 | 1369 |
Frequently asked questions
Is GPT-4 Turbo better than Nemotron 3 Super?
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 30.5 on the Noometry Index.
Which is cheaper, GPT-4 Turbo 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-4 Turbo lists at $10 and $30.
Is GPT-4 Turbo or Nemotron 3 Super better for coding?
Nemotron 3 Super scores higher on coding benchmarks: 39.4 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3 Super does, with 262K tokens against 128K.
How many benchmarks do GPT-4 Turbo and Nemotron 3 Super share?
16 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Nemotron 3 Super has 21.