- Intelligence
- 6.8
- Rank 584 of 744 measured models
- Output speed
- 170 t/s
- Rank 60 of 403 measured models
- Price/1M
- $0.086
- Rank 76 of 659 measured models
- Context window
- 131K
- Rank 738 of 1199 measured models
NVIDIA Nemotron Nano 9B V2 (Non-reasoning) scores 6.8 on the Artificial Analysis Intelligence Index, ranking 584th of 744 measured models. The closest models on this index are Mistral Large 2 (Jul '24) (6.8), NVIDIA Nemotron 3 Nano 30B A3B (6.8), and GLM-4.5V (6.7). At $0.086 per million tokens (3:1 input/output blended price), it is cheaper than Mistral Large 2 (Jul '24) ($3) and GLM-4.5V ($0.90), priced close to NVIDIA Nemotron 3 Nano 30B A3B ($0.088). With an output speed of 170 t/s, it is faster than GLM-4.5V (46.3 t/s), slower than NVIDIA Nemotron 3 Nano 30B A3B (250 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Mistral Large 2 (Jul '24)
Mistral · $3 · —
6.8$3—Compare - NVIDIA Nemotron 3 Nano 30B A3B
NVIDIA · $0.088 · 250 t/s
6.8$0.088250 t/sCompare - GLM-4.5V
Z.AI · $0.90 · 46.3 t/s
6.7−0.1$0.9046.3 t/sCompare - GPT-4
OpenAI · $37.50 · —
6.7−0.1$37.50—Compare
