Compare
Gemini 3.1 Pro vs Nemotron 3 Ultra
Gemini 3.1 Pro (Google DeepMind) and Nemotron 3 Ultra (NVIDIA) compared on benchmarks, pricing, context window, and use-case rankings.
| Attribute | Gemini 3.1 Pro | Nemotron 3 Ultra |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 155 | — |
| Coding | 65 | — |
| Math | 74 | — |
| Reasoning & Knowledge | 94 | 29 |
| Agentic & Tools | 83 | 18 |
| Specifications | ||
| Developer | Google DeepMind | NVIDIA |
| Family | Gemini | Nemotron |
| Released | Feb 19, 2026 | Jun 4, 2026 |
| Parameters | — | 550B |
| Availability | API access | Open weights (unrestricted) |
| Context window | — | — |
| Price — $/M input | — | — |
| Price — $/M output | — | — |
| Inputs | — | — |
| Outputs | — | — |
| Benchmarks | ||
| AIME 2024/2025 | 96% | — |
| APEX | 34% | 12% |
| ARC-AGI | 98% | — |
| ARC-AGI-2 | 77% | — |
| FrontierMath | 37% | — |
| FrontierMath Tier 4 | 17% | — |
| GPQA Diamond | 94% | — |
| GSO (code optimization) | 23% | — |
| Humanity's Last Exam | 46% | — |
| METR task horizon | 6.4 h | — |
| SimpleBench | 80% | — |
| SimpleQA Verified | 77% | — |
| SWE-bench Verified | 76% | — |
| Terminal-Bench | 80% | — |
| WebDev Arena | 1461 | — |
| WeirdML | 72% | 43% |
Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.
Want a different match-up? Open the compare tool to add or swap models.
More comparisons
Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.