Gemini 3.7 Flash vs Nemotron 3.5 Lightning 30B A3B
| model Gemini 3.7 Flash Google | model Nemotron 3.5 Lightning 30B A3B NVIDIA | |
|---|---|---|
| Context | 1M | 262K |
| Input $/M | — | — |
| Output $/M | — | — |
| Knowledge cutoff | 2026-03 | — |
| Available via | Gemini API (AI Studio) | weights only (no API yet) |
| FrontierCode (score) | 43.6 | — |
| DeepSWE | 65.3% | — |
| Terminal-Bench (accuracy) | 85.8 | — |
| AutomationBench (accuracy) | 30.4 | — |
| GDP.pdf (accuracy) | 34 | — |
| GDM-MRCR (accuracy) | 97 | — |