modelgrep

Meta: Llama 4 Maverick vs NVIDIA: Llama 3.3 Nemotron Super 49B V1.5

Meta: Llama 4 Maverick wins on more metrics (7 of 9), but the right pick depends on what you optimize for — see the breakdown below.

MetricMeta: Llama 4 MaverickNVIDIA: Llama 3.3 Nemotron Super 49B V1.5
Intelligence Index18.414.6
Coding Index15.610.5
GPQA Diamond67%48%
Design Arena Elo980
Speed (tokens/sec)6541
Latency301ms160ms
Input price /M$0.150$0.400
Output price /M$0.600$0.400
Context window1.0M131K
CapabilitiesToolsJSONVisionReasoningToolsJSON