Model comparison
Gemini 3 Deep Think vs Nemotron 3 Ultra
Nemotron 3 Ultra has enough public results to be ranked (#113); Gemini 3 Deep Think does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
Google
NVIDIASummary
- They share 1 benchmark with published results for both. Gemini 3 Deep Think scores higher in 1 category and Nemotron 3 Ultra in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3 Deep Think leads 70.2 to 31.0.
- The biggest single-benchmark swing is CritPt: 25.7% for Gemini 3 Deep Think and 3.1% for Nemotron 3 Ultra.
- Nemotron 3 Ultra has downloadable open weights; the other is API-only.
Side by side
| Gemini 3 Deep Think | Nemotron 3 Ultra | |
|---|---|---|
| Provider | NVIDIA | |
| Noometry Index | 58.3 | 42.5 |
| Released | 2026-02-12 | 2026-06-04 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.60 |
| Output $ / M tokens | — | $2.40 |
| Results tracked | 3 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Gemini 3 Deep Think: —, Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | Gemini 3 Deep Think | Nemotron 3 Ultra |
|---|---|---|
| FrontierCode | — | 13.6% |
| SciCode | — | 40.3% |
| WeirdML | — | 43.5% |
| LMArena Coding | — | 1468 |
Agentic & Tool Use Not comparable
Gemini 3 Deep Think: —, Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | Gemini 3 Deep Think | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | — | 22.7% |
Reasoning Gemini 3 Deep Think leads
Gemini 3 Deep Think: 70.2 (#14), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | Gemini 3 Deep Think | Nemotron 3 Ultra |
|---|---|---|
| CritPt | 25.7% | 3.1% |
| ARC-AGI-2 | 84.6% | — |
| ARC-AGI-1 | 96% | — |
| Chess Puzzles | — | 12% |
| LMArena Hard Prompts | — | 1452 |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 90.1% |
| LMCA | — | 36.9% |
| Epoch Capabilities Index | — | 146.17 |
Math Not comparable
Gemini 3 Deep Think: —, Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | Gemini 3 Deep Think | Nemotron 3 Ultra |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| ProofBench | — | 2% |
| LMArena Math | — | 1457 |
Knowledge Not comparable
Gemini 3 Deep Think: —, Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | Gemini 3 Deep Think | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | — | 85.4% |
| LMArena Expert | — | 1472 |
Multilingual Not comparable
Gemini 3 Deep Think: —, Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | Gemini 3 Deep Think | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | — | 1427 |
| LMArena Chinese | — | 1497 |
| LMArena French | — | 1472 |
| LMArena German | — | 1471 |
| LMArena Korean | — | 1386 |
| LMArena Russian | — | 1417 |
| LMArena Spanish | — | 1454 |
Instruction Following Not comparable
Gemini 3 Deep Think: —, Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | Gemini 3 Deep Think | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | — | 1418 |
Long Context Not comparable
Gemini 3 Deep Think: —, Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | Gemini 3 Deep Think | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | — | 1437 |
Writing & Preference Not comparable
Gemini 3 Deep Think: —, Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | Gemini 3 Deep Think | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | — | 1445 |
| LMArena Creative Writing | — | 1398 |
| EQ-Bench Creative Writing | — | 1692 |
| LMArena Multi-Turn | — | 1411 |
Frequently asked questions
Is Gemini 3 Deep Think better than Nemotron 3 Ultra?
Nemotron 3 Ultra has enough public results to be ranked (#113); Gemini 3 Deep Think does not yet, so treat this comparison as directional.
How many benchmarks do Gemini 3 Deep Think and Nemotron 3 Ultra share?
1 benchmark has published results for both models. Gemini 3 Deep Think has 3 scored results on Noometry and Nemotron 3 Ultra has 30.