NVIDIA
Nemotron 3.5 Super VL
ReasoningOpen weights
- Intelligence
- 26.5
- Rank 158 of 747 measured models
- Output speed
- 176 t/s
- Rank 63 of 405 measured models
- Price/1M
- $0.35
- Rank 222 of 664 measured models
- Context window
- 1M
- Rank 84 of 1207 measured models
- Cost per task
- $0.303
- Rank 85 of 195 measured models
Nemotron 3.5 Super VL scores 26.5 on the Artificial Analysis Intelligence Index, ranking 158th of 747 measured models. The closest models on this index are GLM-5-Turbo (26.6), Apodex 1.1 (26.4), and Claude Opus 4.6 (26.4). At $0.35 per million tokens (3:1 input/output blended price), it is cheaper than Apodex 1.1 ($0.975) and Claude Opus 4.6 ($10). With an output speed of 176 t/s, it is faster than Claude Opus 4.6 (44.1 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Quasar 438B (Max, Based on GLM-5.2)
Multiverse Computing · $0.90 · 135 t/s
26.7+0.2$0.90135 t/sCompare - GLM-5-Turbo
Z.AI · — · —
26.6+0.1——Compare - Apodex 1.1
Apodex · $0.975 · —
26.4−0.1$0.975—Compare - Claude Opus 4.6
Anthropic · $10 · 44.1 t/s
26.4−0.1$1044.1 t/sCompare
