GPT-4o (Aug '24) vs Llama 3.3 Instruct 70B

OpenAI · Meta · catalog 2026-09-14

Llama 3.3 Instruct 70B beats GPT-4o (Aug '24): cheaper ($0.666 vs $2.375/M) and at least as smart (index 7.7 vs 7.7).

	GPT-4o (Aug '24)	Llama 3.3 Instruct 70B
Speed (tok/s)	88.5 measured	85.8 measured
Blended $/M	$2.375 derived	$0.666 derived
Intelligence index	7.7 measured	7.7 measured
TTFT (ms)	136 measured	166 measured
Context	128k list	—
Coding index	not measured for both
Agentic index	not measured for both

GPT-4o (Aug '24) card · Llama 3.3 Instruct 70B 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.