0

Nemotron 3 Ultra

Publisher
NVIDIA
Context
512K
Input
Output
Released
4 Jun 2026

Cite

Notes

Only stored in your browser.

Attribution

Benchmark scores
AAVals AI
Attribution policy →
Context
512K
Input
$0.68
/1M tok
Output
$2.67
/1M tok
Blended
$1.18
#335/ 461/1M · 3:1
Speed
211
#26/ 461tok/s
Cache read
$0.20
0.30x input

Price & speed via Artificial Analysis · ranked across tracked models · caching via OpenRouter

Reported on 13 evals across 8 domains - best 86.7% on GPQA Diamond · #63 of 494

Reported eval scores

13