# NVIDIA Nemotron 3.5 Super VL

As of October 22, 2026, NVIDIA Nemotron 3.5 Super VL ranks #105 of 123 models overall with 35.6 ±18.2 on the LLMBenchmark Index. Nemotron 3.5 Super VL ranks #65 of 122 in reasoning, its strongest category. NVIDIA Nemotron 3.5 Super VL costs $0.15 per million input tokens and $0.50 per million output tokens. Nemotron 3.5 Super VL was released on October 15, 2026.

Page: https://llmbenchmark.ai/models/nvidia-nemotron-3-5-super-vl
Data from October 22, 2026. Every figure below names the board it was read from and the day.

- Maker: NVIDIA
- Released: October 15, 2026
- Price per million input tokens: $0.15
- Price per million output tokens: $0.50
- Context window: 1.05M tokens
- Overall rank: 105 of 123, by the LLMBenchmark Index
- LLMBenchmark Index: 35.6 ±18.2 (90% margin, from 3 of 7 inputs)
- Artificial Analysis Intelligence Index: 26.5
- Vibe Coding Index: not enough data (one index benchmark; at least two are needed to rank)

Benchmark results (16 of 195):

- LiveBench coding: 65.5% (source: LiveBench, read October 22, 2026)
- AA Intelligence Index: 26.5 (source: Artificial Analysis (via OpenRouter), read October 22, 2026)
- Design Arena: websites: 1172 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: UI components: 1153 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: game dev: 1110 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: 3D: 1127 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: all code categories: 1155 Elo (source: Design Arena, read October 22, 2026)
- LiveBench reasoning: 78.8% (source: LiveBench, read October 22, 2026)
- LiveBench data analysis: 64.6% (source: LiveBench, read October 22, 2026)
- LiveBench research: 70.9% (source: LiveBench, read October 22, 2026)
- LiveBench browser: 4.0% (source: LiveBench, read October 22, 2026)
- LiveBench long agentic: 15.8% (source: LiveBench, read October 22, 2026)
- LiveBench design: 60.7% (source: LiveBench, read October 22, 2026)
- Humanity's Last Exam (Artificial Analysis run): 30.7% (source: Artificial Analysis, read October 22, 2026)
- SciCode: 47.8% (source: Artificial Analysis, read October 22, 2026)
- Long context reasoning (AA-LCR): 69.0% (source: Artificial Analysis, read October 22, 2026)