GPT-5.4 nano (Non-Reasoning) vs HyperNova 60B 2605 (high, based on gpt-oss-120b)

OpenAI · Multiverse Computing · catalog 2026-09-14

HyperNova 60B 2605 (high, based on gpt-oss-120b) beats GPT-5.4 nano (Non-Reasoning): cheaper ($0.05 vs $0.179/M) and at least as smart (index 11.7 vs 11.7).

	GPT-5.4 nano (Non-Reasoning)	HyperNova 60B 2605 (high, based on gpt-oss-120b)
Speed (tok/s)	164.4 measured	360.5 measured
Blended $/M	$0.179 derived	$0.05 derived
Intelligence index	11.7 measured	11.7 measured
TTFT (ms)	84 measured	6 measured
Context	—	—
Coding index	not measured for both
Agentic index	not measured for both

GPT-5.4 nano (Non-Reasoning) card · HyperNova 60B 2605 (high, based on gpt-oss-120b) card · 3D observatory

Verdicts use price×intelligence dominance only, and only where both sides are measured; null cells stay null with their provenance (em-dash = not in catalog). Percentile-free by design — this page compares two models, not the field. Generated page — do not hand-edit.