Model comparison
Gemini 3 Flash Preview vs Nemotron 3 Ultra
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 42.5 on the Noometry Index.
Last verified . 25 shared benchmarks.
Google
NVIDIASummary
- They share 25 benchmarks with published results for both. Gemini 3 Flash Preview scores higher in 8 categories and Nemotron 3 Ultra in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3 Flash Preview leads 49.2 to 31.0.
- The biggest single-benchmark swing is Chess Puzzles: 40% for Gemini 3 Flash Preview and 12% for Nemotron 3 Ultra.
- Nemotron 3 Ultra is cheaper at $0.50 / $2.20 per million input/output tokens, against $0.50 / $3 for Gemini 3 Flash Preview.
- Gemini 3 Flash Preview 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 Flash Preview | Nemotron 3 Ultra | |
|---|---|---|
| Provider | NVIDIA | |
| Noometry Index | 52.3 | 42.5 |
| Released | 2025-12-17 | 2026-06-04 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 66K | 128K |
| Input $ / M tokens | $0.50 | $0.50 |
| Output $ / M tokens | $3 | $2.20 |
| Results tracked | 59 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 50.9 (#42), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | Gemini 3 Flash Preview | Nemotron 3 Ultra |
|---|---|---|
| WeirdML | 61.6% | 43.5% |
| LMArena Coding | 1460 | 1468 |
| SWE-bench Verified | 75.4% | — |
| FrontierCode | — | 13.6% |
| SWE-bench Verified (bash only) | 75.8% | — |
| LMArena WebDev | 1439 | — |
| SWE-bench Multilingual | 72.7% | — |
| SciCode | — | 40.3% |
| GSO | 9.8% | — |
| ALE-Bench | 1,367 | — |
Agentic & Tool Use Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 38.7 (#29), Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | Gemini 3 Flash Preview | Nemotron 3 Ultra |
|---|---|---|
| Terminal-Bench | 64.3% | — |
| APEX-Agents | — | 22.7% |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 27.3% | — |
| τ²-bench Retail | 76.8% | — |
| τ²-bench Telecom | 91.2% | — |
| DeepResearch Bench | 49.8% | — |
| BALROG | 48.1% | — |
| GDP.pdf | 10% | — |
| LMArena Search | 1198 | — |
| Vending-Bench 2 | 3,635 | — |
Reasoning Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 49.2 (#37), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | Gemini 3 Flash Preview | Nemotron 3 Ultra |
|---|---|---|
| Chess Puzzles | 40% | 12% |
| LMArena Hard Prompts | 1465 | 1452 |
| Mystery Game Puzzles | 26% | 20% |
| DTBench | 89.1% | 90.1% |
| LMCA | 43.1% | 36.9% |
| Epoch Capabilities Index | 151.8 | 146.17 |
| ARC-AGI-2 | 33.6% | — |
| SimpleBench | 61.1% | — |
| NYT Connections (extended) | 83.1% | — |
| ARC-AGI-1 | 84.7% | — |
| CritPt | — | 3.1% |
| ForecastBench | 58.5 | — |
Math Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 51.7 (#55), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | Gemini 3 Flash Preview | Nemotron 3 Ultra |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 95.6% | 86.7% |
| ProofBench | 15% | 2% |
| LMArena Math | 1473 | 1457 |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 17.1% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| FrontierMath (Feb 2025 set) | 35.6% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 58.8 (#33), Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | Gemini 3 Flash Preview | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | 89.4% | 85.4% |
| LMArena Expert | 1462 | 1472 |
| SimpleQA Verified | 66.8% | — |
| Vectara Hallucination Rate | 13.5% | — |
Multimodal Not comparable
Gemini 3 Flash Preview: 45.5 (#16), Nemotron 3 Ultra: —
| Benchmark | Gemini 3 Flash Preview | Nemotron 3 Ultra |
|---|---|---|
| LMArena Vision | 1285 | — |
| GeoBench | 88% | — |
| VPCT | 72.6% | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1413 | — |
Multilingual Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 55.7 (#27), Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | Gemini 3 Flash Preview | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1458 | 1427 |
| LMArena Chinese | 1511 | 1497 |
| LMArena French | 1477 | 1472 |
| LMArena German | 1497 | 1471 |
| LMArena Korean | 1443 | 1386 |
| LMArena Russian | 1480 | 1417 |
| LMArena Spanish | 1469 | 1454 |
| LMArena Japanese | 1489 | — |
Instruction Following Too close to call
Gemini 3 Flash Preview: 75.7 (#56), Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | Gemini 3 Flash Preview | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1437 | 1418 |
Long Context Too close to call
Gemini 3 Flash Preview: 44.4 (#67), Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | Gemini 3 Flash Preview | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1452 | 1437 |
Writing & Preference Too close to call
Gemini 3 Flash Preview: 65.5 (#45), Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | Gemini 3 Flash Preview | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1466 | 1445 |
| LMArena Creative Writing | 1457 | 1398 |
| LMArena Multi-Turn | 1471 | 1411 |
| EQ-Bench Creative Writing | — | 1692 |
Frequently asked questions
Is Gemini 3 Flash Preview better than Nemotron 3 Ultra?
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 42.5 on the Noometry Index.
Which is cheaper, Gemini 3 Flash Preview or Nemotron 3 Ultra?
Nemotron 3 Ultra is cheaper. It lists at $0.50 per million input tokens and $2.20 per million output tokens; Gemini 3 Flash Preview lists at $0.50 and $3.
Is Gemini 3 Flash Preview or Nemotron 3 Ultra better for coding?
Gemini 3 Flash Preview scores higher on coding benchmarks: 50.9 versus 38.1 in the Noometry coding category.
Which has the bigger context window?
Gemini 3 Flash Preview does, with 1.05M tokens against 262K.
How many benchmarks do Gemini 3 Flash Preview and Nemotron 3 Ultra share?
25 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and Nemotron 3 Ultra has 30.