AI Benchmark Model
Grok 4.6 (high)
Benchmark scores, pricing, speed, and model comparisons for Grok 4.6 (high).
Key scores
Grok 4.6 (high) is an artificial intelligence model developed by SpaceXAI and released on August 12, 2026. In terms of performance metrics, the model achieves an intelligence index of 60.9 and a coding index of 76.8. Benchmark results for the model include a GPQA score of 0.949, an HLE score of 0.429, a SciCode score of 0.536, and an LCR score of 0.75. Regarding operational speed, the model provides an output speed of 67.375 tokens per second with a time to first token of 49.322 seconds. Pricing for Grok 4.6 (high) is set at $2.00 per million tokens for input and $6.00 per million tokens for output, resulting in a blended rate of $3.00 per million tokens.
Benchmark results
4 tracked benchmark rows for Grok 4.6 (high).
GPQA Reasoning
94.9% LCR Other
75.0% SciCode Other
53.6% HLE Other
42.9%
Comments (0)
to join the discussion
No comments yet
Be the first to share your thoughts!