Model comparison
Nemotron 3 Super vs Trinity Large Thinking
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 38.6 on the Noometry Index.
Last verified . 18 shared benchmarks.
NVIDIA
Arcee AISummary
- They share 18 benchmarks with published results for both. Nemotron 3 Super scores higher in 7 categories and Trinity Large Thinking in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in coding, where Nemotron 3 Super leads 39.4 to 34.1.
- Nemotron 3 Super is cheaper at $0.08 / $0.45 per million input/output tokens, against $0.25 / $0.80 for Trinity Large Thinking.
Side by side
| Nemotron 3 Super | Trinity Large Thinking | |
|---|---|---|
| Provider | NVIDIA | Arcee AI |
| Noometry Index | 40.1 | 38.6 |
| Released | 2026-03-11 | 2026-04-01 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 131K | 80K |
| Input $ / M tokens | $0.08 | $0.25 |
| Output $ / M tokens | $0.45 | $0.80 |
| Results tracked | 21 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Super leads
Nemotron 3 Super: 39.4 (#158), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Nemotron 3 Super | Trinity Large Thinking |
|---|---|---|
| SciCode | 36% | 36.1% |
| LMArena Coding | 1403 | 1381 |
| LMArena WebDev | — | 1238 |
| WeirdML | 38% | — |
| ALE-Bench | 213.9 | — |
Reasoning Nemotron 3 Super leads
Nemotron 3 Super: 18.7 (#276), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Nemotron 3 Super | Trinity Large Thinking |
|---|---|---|
| NYT Connections (extended) | 15.4% | 16.5% |
| CritPt | 3.1% | 0.9% |
| LMArena Hard Prompts | 1386 | 1350 |
| Thematic Generalization | — | 41.6% |
| Surface Evolver Bench | — | 15.6% |
Math Nemotron 3 Super leads
Nemotron 3 Super: 39.6 (#101), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Nemotron 3 Super | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1380 | 1366 |
| MathArena Final-Answer Competitions | 60.4% | — |
Knowledge Trinity Large Thinking leads
Nemotron 3 Super: 38.9 (#139), Trinity Large Thinking: 40.9 (#113)
| Benchmark | Nemotron 3 Super | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1398 | 1360 |
| Vectara Hallucination Rate | — | 6.9% |
Multilingual Nemotron 3 Super leads
Nemotron 3 Super: 48.4 (#144), Trinity Large Thinking: 46.2 (#160)
| Benchmark | Nemotron 3 Super | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1355 | 1325 |
| LMArena Chinese | 1432 | 1373 |
| LMArena French | 1405 | 1374 |
| LMArena German | 1341 | 1356 |
| LMArena Russian | 1336 | 1337 |
| LMArena Spanish | 1417 | 1357 |
| LMArena Japanese | — | 1311 |
| LMArena Korean | — | 1306 |
Instruction Following Too close to call
Nemotron 3 Super: 71.2 (#154), Trinity Large Thinking: 70.5 (#162)
| Benchmark | Nemotron 3 Super | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1347 | 1334 |
Long Context Too close to call
Nemotron 3 Super: 41.5 (#139), Trinity Large Thinking: 41.3 (#144)
| Benchmark | Nemotron 3 Super | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1362 | 1355 |
Writing & Preference Nemotron 3 Super leads
Nemotron 3 Super: 55.9 (#140), Trinity Large Thinking: 53.8 (#158)
| Benchmark | Nemotron 3 Super | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1378 | 1340 |
| LMArena Creative Writing | 1317 | 1320 |
| LMArena Multi-Turn | 1369 | 1342 |
Frequently asked questions
Is Nemotron 3 Super better than Trinity Large Thinking?
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 38.6 on the Noometry Index.
Which is cheaper, Nemotron 3 Super or Trinity Large Thinking?
Nemotron 3 Super is cheaper. It lists at $0.08 per million input tokens and $0.45 per million output tokens; Trinity Large Thinking lists at $0.25 and $0.80.
Is Nemotron 3 Super or Trinity Large Thinking better for coding?
Nemotron 3 Super scores higher on coding benchmarks: 39.4 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Nemotron 3 Super and Trinity Large Thinking share?
18 benchmarks have published results for both models. Nemotron 3 Super has 21 scored results on Noometry and Trinity Large Thinking has 24.