Model comparison
Mercury 2 vs Nemotron 3 Super
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 39.1 on the Noometry Index.
Last verified . 15 shared benchmarks.
NVIDIASummary
- They share 15 benchmarks with published results for both. Mercury 2 scores higher in 1 category and Nemotron 3 Super in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in coding, where Nemotron 3 Super leads 39.4 to 33.5.
- The biggest single-benchmark swing is WeirdML: 43.2% for Mercury 2 and 38% for Nemotron 3 Super.
- Nemotron 3 Super is cheaper at $0.08 / $0.45 per million input/output tokens, against $0.25 / $0.75 for Mercury 2.
- 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
| Mercury 2 | Nemotron 3 Super | |
|---|---|---|
| Provider | Inception | NVIDIA |
| Noometry Index | 39.1 | 40.1 |
| Released | 2026-02-20 | 2026-03-11 |
| Weights | Proprietary | Open |
| Context window | 128K | 262K |
| Max output | 50K | 131K |
| Input $ / M tokens | $0.25 | $0.08 |
| Output $ / M tokens | $0.75 | $0.45 |
| Results tracked | 17 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Super leads
Mercury 2: 33.5 (#255), Nemotron 3 Super: 39.4 (#158)
| Benchmark | Mercury 2 | Nemotron 3 Super |
|---|---|---|
| SciCode | 38.7% | 36% |
| WeirdML | 43.2% | 38% |
| LMArena Coding | 1391 | 1403 |
| ALE-Bench | 785.58 | 213.9 |
| LMArena WebDev | 1171 | — |
Reasoning Mercury 2 leads
Mercury 2: 23.8 (#170), Nemotron 3 Super: 18.7 (#276)
| Benchmark | Mercury 2 | Nemotron 3 Super |
|---|---|---|
| CritPt | 0.8% | 3.1% |
| LMArena Hard Prompts | 1362 | 1386 |
| NYT Connections (extended) | — | 15.4% |
Math Not comparable
Mercury 2: —, Nemotron 3 Super: 39.6 (#101)
| Benchmark | Mercury 2 | Nemotron 3 Super |
|---|---|---|
| MathArena Final-Answer Competitions | — | 60.4% |
| LMArena Math | — | 1380 |
Knowledge Nemotron 3 Super leads
Mercury 2: 36.2 (#172), Nemotron 3 Super: 38.9 (#139)
| Benchmark | Mercury 2 | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | 1358 | 1398 |
| Vectara Hallucination Rate | 12.3% | — |
Multilingual Nemotron 3 Super leads
Mercury 2: 46.6 (#157), Nemotron 3 Super: 48.4 (#144)
| Benchmark | Mercury 2 | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1331 | 1355 |
| LMArena Chinese | 1417 | 1432 |
| LMArena Russian | 1304 | 1336 |
| LMArena French | — | 1405 |
| LMArena German | — | 1341 |
| LMArena Spanish | — | 1417 |
Instruction Following Too close to call
Mercury 2: 70.2 (#165), Nemotron 3 Super: 71.2 (#154)
| Benchmark | Mercury 2 | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1329 | 1347 |
Long Context Nemotron 3 Super leads
Mercury 2: 40.5 (#154), Nemotron 3 Super: 41.5 (#139)
| Benchmark | Mercury 2 | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1330 | 1362 |
Writing & Preference Nemotron 3 Super leads
Mercury 2: 53.8 (#155), Nemotron 3 Super: 55.9 (#140)
| Benchmark | Mercury 2 | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1355 | 1378 |
| LMArena Creative Writing | 1289 | 1317 |
| LMArena Multi-Turn | 1358 | 1369 |
Frequently asked questions
Is Mercury 2 better than Nemotron 3 Super?
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 39.1 on the Noometry Index.
Which is cheaper, Mercury 2 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; Mercury 2 lists at $0.25 and $0.75.
Is Mercury 2 or Nemotron 3 Super better for coding?
Nemotron 3 Super scores higher on coding benchmarks: 39.4 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3 Super does, with 262K tokens against 128K.
How many benchmarks do Mercury 2 and Nemotron 3 Super share?
15 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Nemotron 3 Super has 21.