- Intelligence
- 12.9
- Rank 350 of 744 measured models
- Coding
- 26.8
- Rank 191 of 298 measured models
- Output speed
- 302 t/s
- Rank 12 of 403 measured models
- Price/1M
- $0.095
- Rank 84 of 659 measured models
- Context window
- 1M
- Rank 84 of 1199 measured models
- Cost per task
- $0.0931
- Rank 51 of 193 measured models
Nemotron 3.5 Lightning scores 12.9 on the Artificial Analysis Intelligence Index, ranking 350th of 744 measured models. The closest models on this index are GPT-5 nano (13.0), GLM-4.5 (Reasoning) (12.8), and Nemotron 3 Super 120B A12B (12.8). At $0.095 per million tokens (3:1 input/output blended price), it is cheaper than GPT-5 nano ($0.138) and Nemotron 3 Super 120B A12B ($0.45). With an output speed of 302 t/s, it is faster than GPT-5 nano (162 t/s) and Nemotron 3 Super 120B A12B (146 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- DeepSeek R1 0528 (May '25)
DeepSeek · $1.76 · 33.9 t/s
13.1+0.2$1.7633.9 t/sCompare - GPT-5 nano
OpenAI · $0.138 · 162 t/s
13.0+0.1$0.138162 t/sCompare - GLM-4.5 (Reasoning)
Z.AI · — · —
12.8−0.1——Compare - Nemotron 3 Super 120B A12B
NVIDIA · $0.45 · 146 t/s
12.8−0.1$0.45146 t/sCompare
