Model comparison
Nemotron 4 340b Instruct vs Trinity Large Thinking
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 35.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
NVIDIA
Arcee AISummary
- They share 17 benchmarks with published results for both. Nemotron 4 340b Instruct scores higher in 2 categories and Trinity Large Thinking in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Trinity Large Thinking leads 53.8 to 42.7.
Side by side
| Nemotron 4 340b Instruct | Trinity Large Thinking | |
|---|---|---|
| Provider | NVIDIA | Arcee AI |
| Noometry Index | 35.9 | 38.6 |
| Released | 2024-06-14 | 2026-04-01 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 80K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.80 |
| Results tracked | 17 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 4 340b Instruct leads
Nemotron 4 340b Instruct: 35.2 (#228), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Nemotron 4 340b Instruct | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1209 | 1381 |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
Reasoning Nemotron 4 340b Instruct leads
Nemotron 4 340b Instruct: 23.4 (#178), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Nemotron 4 340b Instruct | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1202 | 1350 |
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 41.6% |
| Surface Evolver Bench | — | 15.6% |
Math Trinity Large Thinking leads
Nemotron 4 340b Instruct: 34.3 (#195), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Nemotron 4 340b Instruct | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1216 | 1366 |
Knowledge Trinity Large Thinking leads
Nemotron 4 340b Instruct: 32.0 (#216), Trinity Large Thinking: 40.9 (#113)
| Benchmark | Nemotron 4 340b Instruct | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1171 | 1360 |
| Vectara Hallucination Rate | — | 6.9% |
Multilingual Trinity Large Thinking leads
Nemotron 4 340b Instruct: 37.9 (#233), Trinity Large Thinking: 46.2 (#160)
| Benchmark | Nemotron 4 340b Instruct | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1206 | 1325 |
| LMArena Chinese | 1214 | 1373 |
| LMArena French | 1197 | 1374 |
| LMArena German | 1192 | 1356 |
| LMArena Japanese | 1128 | 1311 |
| LMArena Korean | 1148 | 1306 |
| LMArena Russian | 1219 | 1337 |
| LMArena Spanish | 1195 | 1357 |
Instruction Following Trinity Large Thinking leads
Nemotron 4 340b Instruct: 63.1 (#232), Trinity Large Thinking: 70.5 (#162)
| Benchmark | Nemotron 4 340b Instruct | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1203 | 1334 |
Long Context Trinity Large Thinking leads
Nemotron 4 340b Instruct: 37.1 (#221), Trinity Large Thinking: 41.3 (#144)
| Benchmark | Nemotron 4 340b Instruct | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1225 | 1355 |
Writing & Preference Trinity Large Thinking leads
Nemotron 4 340b Instruct: 42.7 (#233), Trinity Large Thinking: 53.8 (#158)
| Benchmark | Nemotron 4 340b Instruct | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1225 | 1340 |
| LMArena Creative Writing | 1203 | 1320 |
| LMArena Multi-Turn | 1214 | 1342 |
Frequently asked questions
Is Nemotron 4 340b Instruct better than Trinity Large Thinking?
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 35.9 on the Noometry Index.
Is Nemotron 4 340b Instruct or Trinity Large Thinking better for coding?
Nemotron 4 340b Instruct scores higher on coding benchmarks: 35.2 versus 34.1 in the Noometry coding category.
How many benchmarks do Nemotron 4 340b Instruct and Trinity Large Thinking share?
17 benchmarks have published results for both models. Nemotron 4 340b Instruct has 17 scored results on Noometry and Trinity Large Thinking has 24.