Nemotron 3.5 Lightning
NVIDIA
SpeedsterOpen weights- Intelligence12.9
- Hallucination38%
- Context1M
- KnowledgeSep 2025
- Speed307tok/s
- Response8.7s
- Price$0.10
- Modalities2
Nemotron 3.5 Lightning
NVIDIA · Built for raw tokens per second. The only cards that can beat the Super Trump.
Card stats
Intelligence ▲ higher wins
Intelligence Index: a composite score from 10 hard evaluations covering reasoning, knowledge, coding, agents and science.
12.9
beats 19% of deck
Hallucination ▼ lower wins
Hallucination rate: of the questions a model gets wrong, how often it confidently makes up an answer instead of saying it doesn't know. Lower wins.
38 %
beats 74% of deck
Context ▲ higher wins
Context window: how many tokens of input the model can consider at once.
1M
beats 65% of deck
Knowledge ▲ higher wins
Training-data cutoff: the most recent month the model learned about. Later wins. N/D means the lab hasn't disclosed it, and an N/D card loses this stat.
Sep 2025
beats 61% of deck
Speed ▲ higher wins
Median output speed in tokens per second, measured on the labs' own APIs.
307 tok/s
beats 90% of deck
Response ▼ lower wins
End-to-end response time: seconds to receive a 500-token answer, thinking time included. Lower wins.
8.7 s
beats 87% of deck
Price ▼ lower wins
Blended price per million tokens (3:1 input to output). Lower wins.
$0.10
beats 100% of deck
Modalities ▲ higher wins
Number of supported input and output modalities: text, image, audio and video.
2
beats 8% of deck
Knowledge: Pre-training cutoff; post-training data to May 2026
Model facts
- Released
- 2026-08-11
- Weights
- Open · OpenMDW-1.1
- Parameters
- 31.6B (3.6B active)
- Reasoning
- Yes
- Price in / out
- $0.06 / $0.2 per 1M
- Time to first token
- 0.57 s
- Humanity’s Last Exam
- 10.6%
- GPQA Diamond
- 74.3%
- SciCode
- 32.1%