Model comparison
Nemotron 3 Ultra vs Nova 2 Lite
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 39.7 on the Noometry Index.
Last verified . 16 shared benchmarks.
Summary
- They share 16 benchmarks with published results for both. Nemotron 3 Ultra scores higher in 6 categories and Nova 2 Lite in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Nemotron 3 Ultra leads 66.3 to 53.9.
- Nova 2 Lite is cheaper at $0.30 / $2.50 per million input/output tokens, against $0.50 / $2.20 for Nemotron 3 Ultra.
- Nova 2 Lite accepts more context: 1M tokens versus 262K.
- Nemotron 3 Ultra has downloadable open weights; the other is API-only.
Side by side
| Nemotron 3 Ultra | Nova 2 Lite | |
|---|---|---|
| Provider | NVIDIA | Amazon |
| Noometry Index | 42.5 | 39.7 |
| Released | 2026-06-04 | 2025-12-01 |
| Weights | Open | Proprietary |
| Context window | 262K | 1M |
| Max output | 128K | 64K |
| Input $ / M tokens | $0.50 | $0.30 |
| Output $ / M tokens | $2.20 | $2.50 |
| Results tracked | 30 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nova 2 Lite leads
Nemotron 3 Ultra: 38.1 (#182), Nova 2 Lite: 40.7 (#134)
| Benchmark | Nemotron 3 Ultra | Nova 2 Lite |
|---|---|---|
| LMArena Coding | 1468 | 1385 |
| FrontierCode | 13.6% | — |
| SciCode | 40.3% | — |
| WeirdML | 43.5% | — |
Agentic & Tool Use Too close to call
Nemotron 3 Ultra: 23.4 (#126), Nova 2 Lite: 24.1 (#121)
| Benchmark | Nemotron 3 Ultra | Nova 2 Lite |
|---|---|---|
| APEX-Agents | 22.7% | — |
| Berkeley Function Calling Leaderboard | — | 27.1% |
Reasoning Nemotron 3 Ultra leads
Nemotron 3 Ultra: 31.0 (#82), Nova 2 Lite: 27.5 (#118)
| Benchmark | Nemotron 3 Ultra | Nova 2 Lite |
|---|---|---|
| LMArena Hard Prompts | 1452 | 1364 |
| CritPt | 3.1% | — |
| Chess Puzzles | 12% | — |
| Mystery Game Puzzles | 20% | — |
| DTBench | 90.1% | — |
| LMCA | 36.9% | — |
| Epoch Capabilities Index | 146.17 | — |
Math Nova 2 Lite leads
Nemotron 3 Ultra: 35.3 (#187), Nova 2 Lite: 37.5 (#156)
| Benchmark | Nemotron 3 Ultra | Nova 2 Lite |
|---|---|---|
| LMArena Math | 1457 | 1359 |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| ProofBench | 2% | — |
Knowledge Nemotron 3 Ultra leads
Nemotron 3 Ultra: 52.5 (#61), Nova 2 Lite: 43.0 (#94)
| Benchmark | Nemotron 3 Ultra | Nova 2 Lite |
|---|---|---|
| LMArena Expert | 1472 | 1358 |
| GPQA Diamond | 85.4% | — |
| Vectara Hallucination Rate | — | 5.1% |
Multilingual Nemotron 3 Ultra leads
Nemotron 3 Ultra: 53.5 (#64), Nova 2 Lite: 47.1 (#153)
| Benchmark | Nemotron 3 Ultra | Nova 2 Lite |
|---|---|---|
| LMArena Non-English | 1427 | 1337 |
| LMArena Chinese | 1497 | 1364 |
| LMArena French | 1472 | 1381 |
| LMArena German | 1471 | 1343 |
| LMArena Korean | 1386 | 1284 |
| LMArena Russian | 1417 | 1343 |
| LMArena Spanish | 1454 | 1373 |
| LMArena Japanese | — | 1271 |
Instruction Following Nemotron 3 Ultra leads
Nemotron 3 Ultra: 74.7 (#88), Nova 2 Lite: 70.5 (#161)
| Benchmark | Nemotron 3 Ultra | Nova 2 Lite |
|---|---|---|
| LMArena Instruction Following | 1418 | 1335 |
Long Context Nemotron 3 Ultra leads
Nemotron 3 Ultra: 43.9 (#81), Nova 2 Lite: 40.6 (#150)
| Benchmark | Nemotron 3 Ultra | Nova 2 Lite |
|---|---|---|
| LMArena Longer Query | 1437 | 1335 |
Writing & Preference Nemotron 3 Ultra leads
Nemotron 3 Ultra: 66.3 (#36), Nova 2 Lite: 53.9 (#154)
| Benchmark | Nemotron 3 Ultra | Nova 2 Lite |
|---|---|---|
| LMArena Text | 1445 | 1362 |
| LMArena Creative Writing | 1398 | 1291 |
| LMArena Multi-Turn | 1411 | 1338 |
| EQ-Bench Creative Writing | 1692 | — |
Frequently asked questions
Is Nemotron 3 Ultra better than Nova 2 Lite?
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 39.7 on the Noometry Index.
Which is cheaper, Nemotron 3 Ultra or Nova 2 Lite?
Nova 2 Lite is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Nemotron 3 Ultra lists at $0.50 and $2.20.
Is Nemotron 3 Ultra or Nova 2 Lite better for coding?
Nova 2 Lite scores higher on coding benchmarks: 40.7 versus 38.1 in the Noometry coding category.
Which has the bigger context window?
Nova 2 Lite does, with 1M tokens against 262K.
How many benchmarks do Nemotron 3 Ultra and Nova 2 Lite share?
16 benchmarks have published results for both models. Nemotron 3 Ultra has 30 scored results on Noometry and Nova 2 Lite has 19.