Model comparison
Gemini 2.0 Flash (Feb 2025) vs Nemotron 3 Ultra
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 35.1 on the Noometry Index.
Last verified . 22 shared benchmarks.
Google
NVIDIASummary
- They share 22 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 2 categories and Nemotron 3 Ultra in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 32.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 57.8% for Gemini 2.0 Flash (Feb 2025) and 86.7% for Nemotron 3 Ultra.
- Nemotron 3 Ultra has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.0 Flash (Feb 2025) | Nemotron 3 Ultra | |
|---|---|---|
| Provider | NVIDIA | |
| Noometry Index | 35.1 | 42.5 |
| Released | 2024-12-06 | 2026-06-04 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.50 |
| Output $ / M tokens | — | $2.20 |
| Results tracked | 54 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Ultra leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Nemotron 3 Ultra |
|---|---|---|
| WeirdML | 25.8% | 43.5% |
| LMArena Coding | 1350 | 1468 |
| FrontierCode | — | 13.6% |
| SWE-bench Verified (bash only) | 13.5% | — |
| Aider Polyglot | 38.2% | — |
| SciCode | — | 40.3% |
| BigCodeBench Instruct | 45.9% | — |
| LiveBench Coding | 63.4% | — |
| BigCodeBench Complete | 59.9% | — |
| CadEval | 30% | — |
Agentic & Tool Use Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | — | 22.7% |
| TheAgentCompany | 11.4% | — |
Reasoning Nemotron 3 Ultra leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Nemotron 3 Ultra |
|---|---|---|
| LMArena Hard Prompts | 1346 | 1452 |
| DTBench | 63.2% | 90.1% |
| Epoch Capabilities Index | 135.36 | 146.17 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 31.1% | — |
| Kagi LLM Benchmark | 37.8% | — |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| EnigmaEval | 1.1% | — |
| LiveBench Reasoning | 78.2% | — |
| Mystery Game Puzzles | — | 20% |
| LiveBench Data Analysis | 69.4% | — |
| LMCA | — | 36.9% |
| LiveBench | 66.9% | — |
Math Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Nemotron 3 Ultra |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 86.7% |
| LMArena Math | 1352 | 1457 |
| ProofBench | — | 2% |
| Omni-MATH | 45.9% | — |
| LiveBench Math | 75.8% | — |
| MATH Level 5 | 82.2% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge Nemotron 3 Ultra leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | 64.1% | 85.4% |
| LMArena Expert | 1339 | 1472 |
| Humanity's Last Exam | 6.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 12.4% | — |
| GPQA (HELM) | 55.6% | — |
| MMLU | 79.7% | — |
Multimodal Not comparable
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), Nemotron 3 Ultra: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Nemotron 3 Ultra |
|---|---|---|
| LMArena Vision | 1158 | — |
| GeoBench | 77% | — |
Multilingual Nemotron 3 Ultra leads
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1342 | 1427 |
| LMArena Chinese | 1373 | 1497 |
| LMArena French | 1391 | 1472 |
| LMArena German | 1353 | 1471 |
| LMArena Korean | 1313 | 1386 |
| LMArena Russian | 1351 | 1417 |
| LMArena Spanish | 1363 | 1454 |
| LMArena Japanese | 1294 | — |
Instruction Following Too close to call
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1336 | 1418 |
| LiveBench Instruction Following | 85.8% | — |
| IFEval | 84.1% | — |
Long Context Nemotron 3 Ultra leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1344 | 1437 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference Nemotron 3 Ultra leads
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1354 | 1445 |
| LMArena Creative Writing | 1340 | 1398 |
| EQ-Bench Creative Writing | 1128 | 1692 |
| LMArena Multi-Turn | 1350 | 1411 |
| Short-Story Creative Writing | 73.8% | — |
| WildBench | 80% | — |
| LiveBench Language | 51.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than Nemotron 3 Ultra?
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 35.1 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or Nemotron 3 Ultra better for coding?
Nemotron 3 Ultra scores higher on coding benchmarks: 38.1 versus 28.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and Nemotron 3 Ultra share?
22 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and Nemotron 3 Ultra has 30.