Model comparison
Gemini 3.5 Flash Lite vs Nemotron 3 Ultra
Gemini 3.5 Flash Lite and Nemotron 3 Ultra score almost the same on the Noometry Index (41.5 vs 42.5), so choose on price, context window or the category you care about most.
Last verified . 29 shared benchmarks.
Google
NVIDIASummary
- They share 29 benchmarks with published results for both. Gemini 3.5 Flash Lite scores higher in 4 categories and Nemotron 3 Ultra in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Nemotron 3 Ultra leads 35.3 to 25.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 71.1% for Gemini 3.5 Flash Lite and 86.7% for Nemotron 3 Ultra.
- Gemini 3.5 Flash Lite is cheaper at $0.30 / $2.50 per million input/output tokens, against $0.50 / $2.20 for Nemotron 3 Ultra.
- Gemini 3.5 Flash Lite accepts more context: 1.05M tokens versus 262K.
- Nemotron 3 Ultra has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.5 Flash Lite | Nemotron 3 Ultra | |
|---|---|---|
| Provider | NVIDIA | |
| Noometry Index | 41.5 | 42.5 |
| Released | 2026-07-21 | 2026-06-04 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 66K | 128K |
| Input $ / M tokens | $0.30 | $0.50 |
| Output $ / M tokens | $2.50 | $2.20 |
| Results tracked | 39 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 42.4 (#104), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | Gemini 3.5 Flash Lite | Nemotron 3 Ultra |
|---|---|---|
| SciCode | 41.3% | 40.3% |
| WeirdML | 39% | 43.5% |
| LMArena Coding | 1453 | 1468 |
| FrontierCode | — | 13.6% |
| LMArena WebDev | 1440 | — |
| ALE-Bench | 765.27 | — |
Agentic & Tool Use Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 25.7 (#107), Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | Gemini 3.5 Flash Lite | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | 29.3% | 22.7% |
| GDP.pdf | 10% | — |
Reasoning Nemotron 3 Ultra leads
Gemini 3.5 Flash Lite: 27.8 (#114), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | Gemini 3.5 Flash Lite | Nemotron 3 Ultra |
|---|---|---|
| CritPt | 0% | 3.1% |
| Chess Puzzles | 22% | 12% |
| LMArena Hard Prompts | 1441 | 1452 |
| Mystery Game Puzzles | 19% | 20% |
| DTBench | 83.5% | 90.1% |
| LMCA | 37.6% | 36.9% |
| Epoch Capabilities Index | 145.13 | 146.17 |
| ARC-AGI-2 | 10.3% | — |
| NYT Connections (extended) | 60.4% | — |
| ARC-AGI-1 | 53.5% | — |
Math Nemotron 3 Ultra leads
Gemini 3.5 Flash Lite: 25.9 (#264), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | Gemini 3.5 Flash Lite | Nemotron 3 Ultra |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 86.7% |
| ProofBench | 13% | 2% |
| LMArena Math | 1433 | 1457 |
| FrontierMath (Tiers 1-3) | 26% | — |
| FrontierMath Tier 4 | 0% | — |
Knowledge Nemotron 3 Ultra leads
Gemini 3.5 Flash Lite: 50.1 (#72), Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | Gemini 3.5 Flash Lite | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | 83.3% | 85.4% |
| LMArena Expert | 1435 | 1472 |
Multimodal Not comparable
Gemini 3.5 Flash Lite: 41.1 (#40), Nemotron 3 Ultra: —
| Benchmark | Gemini 3.5 Flash Lite | Nemotron 3 Ultra |
|---|---|---|
| LMArena Vision | 1268 | — |
Multilingual Too close to call
Gemini 3.5 Flash Lite: 53.5 (#63), Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | Gemini 3.5 Flash Lite | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1427 | 1427 |
| LMArena Chinese | 1469 | 1497 |
| LMArena French | 1451 | 1472 |
| LMArena German | 1454 | 1471 |
| LMArena Korean | 1407 | 1386 |
| LMArena Russian | 1443 | 1417 |
| LMArena Spanish | 1442 | 1454 |
| LMArena Japanese | 1427 | — |
Instruction Following Too close to call
Gemini 3.5 Flash Lite: 74.8 (#85), Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | Gemini 3.5 Flash Lite | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1420 | 1418 |
Long Context Too close to call
Gemini 3.5 Flash Lite: 43.9 (#84), Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | Gemini 3.5 Flash Lite | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1435 | 1437 |
Writing & Preference Nemotron 3 Ultra leads
Gemini 3.5 Flash Lite: 64.2 (#57), Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | Gemini 3.5 Flash Lite | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1435 | 1445 |
| LMArena Creative Writing | 1420 | 1398 |
| EQ-Bench Creative Writing | 1559 | 1692 |
| LMArena Multi-Turn | 1445 | 1411 |
Frequently asked questions
Is Gemini 3.5 Flash Lite better than Nemotron 3 Ultra?
Gemini 3.5 Flash Lite and Nemotron 3 Ultra score almost the same on the Noometry Index (41.5 vs 42.5), so choose on price, context window or the category you care about most.
Which is cheaper, Gemini 3.5 Flash Lite or Nemotron 3 Ultra?
Gemini 3.5 Flash 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 Gemini 3.5 Flash Lite or Nemotron 3 Ultra better for coding?
Gemini 3.5 Flash Lite scores higher on coding benchmarks: 42.4 versus 38.1 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.5 Flash Lite does, with 1.05M tokens against 262K.
How many benchmarks do Gemini 3.5 Flash Lite and Nemotron 3 Ultra share?
29 benchmarks have published results for both models. Gemini 3.5 Flash Lite has 39 scored results on Noometry and Nemotron 3 Ultra has 30.