# NVIDIA Nemotron 3.5 Lightning

NVIDIA Nemotron 3.5 Lightning costs $0.0534 per million input tokens and $0.147 per million output tokens, and it scores 22.6 on the Vibe Coding Index from 2 benchmarks, as of October 21, 2026.

Page: https://llmbenchmark.ai/models/nvidia-nemotron-3-5-lightning
Data from October 21, 2026. Every figure below names the board it was read from and the day.

- Maker: NVIDIA
- Released: August 11, 2026
- Price per million input tokens: $0.0534
- Price per million output tokens: $0.147
- Context window: 262K tokens
- Vibe Coding Index: 22.6 (from 2 of 6 coding benchmarks)

Benchmark results (20 of 195):

- AA Intelligence Index: 12.9 (source: Artificial Analysis (via OpenRouter), read October 21, 2026)
- AA Coding Index: 26.8 (source: Artificial Analysis (via OpenRouter), read October 21, 2026)
- AA Agentic Index: 3.5 (source: Artificial Analysis (via OpenRouter), read October 21, 2026)
- SWE-bench Verified (Vals AI): 52.8% (source: Vals AI boards, read October 21, 2026)
- Vibe Code Bench (Vals AI): 0.0% (source: Vals AI boards, read October 21, 2026)
- Code migration (Vals AI): 3.0% (source: Vals AI boards, read October 21, 2026)
- ProgramBench (Vals AI): 0.0% (source: Vals AI boards, read October 21, 2026)
- Terminal-Bench 2.1 (Vals AI): 10.9% (source: Vals AI boards, read October 21, 2026)
- CyberBench (Vals AI): 29.5% (source: Vals AI boards, read October 21, 2026)
- Finance Agent (Vals AI): 18.5% (source: Vals AI boards, read October 21, 2026)
- Tax Agent Bench (Vals AI): 2.6% (source: Vals AI boards, read October 21, 2026)
- Legal Research Bench (Vals AI): 2.9% (source: Vals AI boards, read October 21, 2026)
- Excel Modeling Benchmark (Vals AI): 17.0% (source: Vals AI boards, read October 21, 2026)
- CorpFin (Vals AI): 54.2% (source: Vals AI boards, read October 21, 2026)
- MedScribe (Vals AI): 4.3% (source: Vals AI boards, read October 21, 2026)
- GPQA Diamond (Artificial Analysis run): 74.3% (source: Artificial Analysis, read October 21, 2026)
- Humanity's Last Exam (Artificial Analysis run): 10.6% (source: Artificial Analysis, read October 21, 2026)
- SciCode: 32.1% (source: Artificial Analysis, read October 21, 2026)
- Long context reasoning (AA-LCR): 60.3% (source: Artificial Analysis, read October 21, 2026)
- ALE-Bench: 769.2 (source: ALE-Bench (Sakana AI), read October 21, 2026)