Grok Beta: Intelligence, Performance & Price Analysis
Analysis of xAI's Grok Beta and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more. Click on any model to compare API providers for that model. For more details including relating to our methodology, see our FAQs.
This is Grok-2 Beta, weights and any other information are not openly released until the next version of Grok is out! https://x.com/elonmusk/status/1842248588149117013
xAI has launched a newer model, Grok 2. We suggest considering this model instead of Grok Beta. See the following pages for a comparison of Grok 2 to other models and Grok 2 API provider benchmarks.
Comparison Summary
Intelligence:
Grok Beta is of higher quality compared to average, with a MMLU score of 0.703 and a Intelligence Index across evaluations of 38.
Price:Grok Beta is more expensive compared to average with a price of $7.50 per 1M Tokens (blended 3:1).
Grok Beta Input token price: $5.00, Output token price: $15.00 per 1M Tokens.
Speed:Grok Beta Input token price: $5.00, Output token price: $15.00 per 1M Tokens.
Grok Beta is slower compared to average, with a output speed of 67.0 tokens per second.
Latency:Grok Beta has a lower latency compared to average, taking 0.29s to receive the first token (TTFT).
Context Window:Grok Beta has a smaller context windows than average, with a context window of 130k tokens.
Highlights
Intelligence
Artificial Analysis Intelligence Index; Higher is better
Speed
Output Tokens per Second; Higher is better
Price
USD per 1M Tokens; Lower is better
Parallel Queries:
Prompt Length:
Grok Beta Model Details
Comparisons to Grok Beta
GPT-4.1 mini
o3
o4-mini (high)
GPT-4.1
Llama 4 Maverick
Llama 4 Scout
Gemma 3 27B Instruct
Gemini 2.5 Pro Preview (Mar' 25)
Gemini 2.5 Flash Preview (May '25) (Reasoning)
Claude 3.7 Sonnet (Extended Thinking)
Mistral Medium 3
DeepSeek R1
DeepSeek V3 0324 (Mar' 25)
Grok 3 mini Reasoning (high)
Grok 3
Nova Premier
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)
Qwen3 235B A22B (Reasoning)
GPT-4o (Nov '24)
Further details