Model comparison
Mercury 2 vs Nemotron 3 Ultra
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 39.1 on the Noometry Index. Mercury 2 costs 2.5× less per token, which makes it the better buy when Nemotron 3 Ultra's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
NVIDIASummary
- They share 14 benchmarks with published results for both. Mercury 2 scores higher in 0 categories and Nemotron 3 Ultra in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 36.2.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.50 / $2.20 for Nemotron 3 Ultra.
- Nemotron 3 Ultra accepts more context: 262K tokens versus 128K.
- Nemotron 3 Ultra has downloadable open weights; the other is API-only.
Side by side
| Mercury 2 | Nemotron 3 Ultra | |
|---|---|---|
| Provider | Inception | NVIDIA |
| Noometry Index | 39.1 | 42.5 |
| Released | 2026-02-20 | 2026-06-04 |
| Weights | Proprietary | Open |
| Context window | 128K | 262K |
| Max output | 50K | 128K |
| Input $ / M tokens | $0.25 | $0.50 |
| Output $ / M tokens | $0.75 | $2.20 |
| Results tracked | 17 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Ultra leads
Mercury 2: 33.5 (#255), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | Mercury 2 | Nemotron 3 Ultra |
|---|---|---|
| SciCode | 38.7% | 40.3% |
| WeirdML | 43.2% | 43.5% |
| LMArena Coding | 1391 | 1468 |
| FrontierCode | — | 13.6% |
| LMArena WebDev | 1171 | — |
| ALE-Bench | 785.58 | — |
Agentic & Tool Use Not comparable
Mercury 2: —, Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | Mercury 2 | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | — | 22.7% |
Reasoning Nemotron 3 Ultra leads
Mercury 2: 23.8 (#170), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | Mercury 2 | Nemotron 3 Ultra |
|---|---|---|
| CritPt | 0.8% | 3.1% |
| LMArena Hard Prompts | 1362 | 1452 |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 90.1% |
| LMCA | — | 36.9% |
| Epoch Capabilities Index | — | 146.17 |
Math Not comparable
Mercury 2: —, Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | Mercury 2 | Nemotron 3 Ultra |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| ProofBench | — | 2% |
| LMArena Math | — | 1457 |
Knowledge Nemotron 3 Ultra leads
Mercury 2: 36.2 (#172), Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | Mercury 2 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Expert | 1358 | 1472 |
| GPQA Diamond | — | 85.4% |
| Vectara Hallucination Rate | 12.3% | — |
Multilingual Nemotron 3 Ultra leads
Mercury 2: 46.6 (#157), Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | Mercury 2 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1331 | 1427 |
| LMArena Chinese | 1417 | 1497 |
| LMArena Russian | 1304 | 1417 |
| LMArena French | — | 1472 |
| LMArena German | — | 1471 |
| LMArena Korean | — | 1386 |
| LMArena Spanish | — | 1454 |
Instruction Following Nemotron 3 Ultra leads
Mercury 2: 70.2 (#165), Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | Mercury 2 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1329 | 1418 |
Long Context Nemotron 3 Ultra leads
Mercury 2: 40.5 (#154), Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | Mercury 2 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1330 | 1437 |
Writing & Preference Nemotron 3 Ultra leads
Mercury 2: 53.8 (#155), Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | Mercury 2 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1355 | 1445 |
| LMArena Creative Writing | 1289 | 1398 |
| LMArena Multi-Turn | 1358 | 1411 |
| EQ-Bench Creative Writing | — | 1692 |
Frequently asked questions
Is Mercury 2 better than Nemotron 3 Ultra?
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 39.1 on the Noometry Index. Mercury 2 costs 2.5× less per token, which makes it the better buy when Nemotron 3 Ultra's lead doesn't matter for your workload.
Which is cheaper, Mercury 2 or Nemotron 3 Ultra?
Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Nemotron 3 Ultra lists at $0.50 and $2.20.
Is Mercury 2 or Nemotron 3 Ultra better for coding?
Nemotron 3 Ultra scores higher on coding benchmarks: 38.1 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3 Ultra does, with 262K tokens against 128K.
How many benchmarks do Mercury 2 and Nemotron 3 Ultra share?
14 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Nemotron 3 Ultra has 30.