Grok 4.3
Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...
Leaderboards
Average Score combining domain-specific Autobench scores; Higher is better
Performance vs. Industry Average
Intelligence
Grok 4.3 is of lower intelligence compared to average (4.5), with an intelligence score of 4.4.
Price
Grok 4.3 is cheaper compared to average ($1.13 per 1M Tokens) with a price of $0.50 per 1M Tokens.
Latency
Grok 4.3 has a lower average latency compared to average (47.46s), with an average latency of 19.37s.
P99 Latency
Grok 4.3 has a lower P99 latency compared to average (288.94s), taking 142.98s to receive the first token at P99 (TTFT).
Context Window
Grok 4.3 has a larger context window than average (453k tokens), with a context window of 1000k tokens.