Model comparison
Gemini 1.5 Pro (May 2024) vs Nemotron 3 Ultra
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 32.1 on the Noometry Index.
Last verified . 21 shared benchmarks.
Google
NVIDIASummary
- They share 21 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 0 categories and Nemotron 3 Ultra in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 29.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 23.1% for Gemini 1.5 Pro (May 2024) and 86.7% for Nemotron 3 Ultra.
- Nemotron 3 Ultra has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Pro (May 2024) | Nemotron 3 Ultra | |
|---|---|---|
| Provider | NVIDIA | |
| Noometry Index | 32.1 | 42.5 |
| Released | 2024-02-15 | 2026-06-04 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.50 |
| Output $ / M tokens | — | $2.20 |
| Results tracked | 45 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Ultra leads
Gemini 1.5 Pro (May 2024): 34.2 (#241), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | Gemini 1.5 Pro (May 2024) | Nemotron 3 Ultra |
|---|---|---|
| WeirdML | 22.2% | 43.5% |
| LMArena Coding | 1294 | 1468 |
| FrontierCode | — | 13.6% |
| SciCode | — | 40.3% |
| BigCodeBench Instruct | 43.8% | — |
| BigCodeBench Complete | 57.5% | — |
| CadEval | 34% | — |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use Nemotron 3 Ultra leads
Gemini 1.5 Pro (May 2024): 17.9 (#145), Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | Gemini 1.5 Pro (May 2024) | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | — | 22.7% |
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| BALROG | 21% | — |
Reasoning Nemotron 3 Ultra leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | Gemini 1.5 Pro (May 2024) | Nemotron 3 Ultra |
|---|---|---|
| LMArena Hard Prompts | 1296 | 1452 |
| DTBench | 59% | 90.1% |
| Epoch Capabilities Index | 131.73 | 146.17 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 27.1% | — |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 20% |
| LMCA | — | 36.9% |
| BIG-Bench Hard | 89.2% | — |
| ForecastBench | 58.4 | — |
Math Nemotron 3 Ultra leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | Gemini 1.5 Pro (May 2024) | Nemotron 3 Ultra |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 86.7% |
| LMArena Math | 1315 | 1457 |
| ProofBench | — | 2% |
| Omni-MATH | 36.4% | — |
| MATH Level 5 | 70.4% | — |
Knowledge Nemotron 3 Ultra leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | Gemini 1.5 Pro (May 2024) | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | 57.2% | 85.4% |
| LMArena Expert | 1279 | 1472 |
| Humanity's Last Exam | 4.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 13.5% | — |
| GPQA (HELM) | 53.4% | — |
| MMLU | 86.9% | — |
Multimodal Not comparable
Gemini 1.5 Pro (May 2024): 36.8 (#77), Nemotron 3 Ultra: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Nemotron 3 Ultra |
|---|---|---|
| LMArena Vision | 1161 | — |
| Video-MME | 75% | — |
Multilingual Nemotron 3 Ultra leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | Gemini 1.5 Pro (May 2024) | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1312 | 1427 |
| LMArena Chinese | 1331 | 1497 |
| LMArena French | 1302 | 1472 |
| LMArena German | 1286 | 1471 |
| LMArena Korean | 1298 | 1386 |
| LMArena Russian | 1320 | 1417 |
| LMArena Spanish | 1311 | 1454 |
| LMArena Japanese | 1292 | — |
Instruction Following Nemotron 3 Ultra leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | Gemini 1.5 Pro (May 2024) | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1297 | 1418 |
| IFEval | 83.7% | — |
Long Context Nemotron 3 Ultra leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | Gemini 1.5 Pro (May 2024) | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1308 | 1437 |
Writing & Preference Nemotron 3 Ultra leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | Gemini 1.5 Pro (May 2024) | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1319 | 1445 |
| LMArena Creative Writing | 1333 | 1398 |
| LMArena Multi-Turn | 1296 | 1411 |
| EQ-Bench Creative Writing | — | 1692 |
| WildBench | 81.3% | — |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than Nemotron 3 Ultra?
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 32.1 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or Nemotron 3 Ultra better for coding?
Nemotron 3 Ultra scores higher on coding benchmarks: 38.1 versus 34.2 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and Nemotron 3 Ultra share?
21 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and Nemotron 3 Ultra has 30.