Report
Nemotron 3.5 Bolt measured at 82,000 output tokens per Intelligence Index task
ArtificialAnlys says that’s 1.8 times Super VL’s 46,000, but 28% fewer than Nemotron 3 Super’s 114,000.
TLDR
ArtificialAnlys reports that Nemotron 3.5 Bolt 74B-A9B 24GB scores 21.4 on the Intelligence Index, fourth among models under 100B parameters and first among US models in that class. It says Bolt uses 82,000 output tokens per Index task, compared with 46,000 for Nemotron 3.5 Super VL and 114,000 for Nemotron 3 Super. Separately, it measured Super VL at about 630 tokens per second on a pre-release DeepInfra endpoint with 100,000-token prompts.
Combined views
—
2 Sources, first seen ago
— likes— comments— saves— reposts
