Skip to content
artificialanalysis.ai·

🤖Grok 4.6 Scores 61 on AI Index, Matches GPT-5.6 Sol

Grok 4.6 matches GPT-5.6 Sol but at a fraction of the cost

TL;DR

SpaceXAI's Grok 4.6 scores 61 on the AI Index, matching GPT-5.6 Sol while costing less per task. It excels in agentic work and offers unmatched value for developers.

Grok 4.6 from SpaceXAI just scored a 61 on the Artificial Analysis Intelligence Index, putting it neck-and-neck with GPT-5.6 Sol but at a fraction of the cost. This matters if you're working on complex projects that require agentic knowledge work and customer service tasks. Grok 4.6 costs $0.84 per task, placing it on the Pareto frontier for performance vs. price. It's notably turn-efficient, completing tasks in ~53 turns and ~0.5B input tokens.

Grok 4.6 Scores 61 on AI Index, Matches GPT-5.6 Sol — artificialanalysis.ai

Key Points

1

Grok 4.6 scores 61 on the Artificial Analysis Intelligence Index, matching GPT-5.6 Sol's score.

2

The model achieves a GDPval-AA v2 Elo of 1753, behind only Claude Opus 5 in real-world agentic knowledge work tasks.

3

Grok 4.6 costs $0.84 per task, making it the most cost-effective option for developers working on complex projects.

4

The model is turn-efficient, completing tasks in ~53 turns and ~0.5B input tokens, compared to Claude Opus 5's ~103 turns and ~2.0B input tokens.

5

Grok 4.6 scores 88.4% on Terminal-Bench v2.1, competitive with leading models.

Why It Matters

If you're working on complex projects that require agentic knowledge work or customer service tasks, Grok 4.6 offers unmatched value at $0.84 per task. Its performance matches GPT-5.6 Sol but is significantly more cost-effective.

GrokAI IndexSpaceXAIcost-efficiencyagentic-work

Frequently Asked Questions

Why does this matter?

If you're working on complex projects that require agentic knowledge work or customer service tasks, Grok 4.6 offers unmatched value at $0.84 per task. Its performance matches GPT-5.6 Sol but is significantly more cost-effective.

What happened?

SpaceXAI's Grok 4.6 scores 61 on the AI Index, matching GPT-5.6 Sol while costing less per task. It excels in agentic work and offers unmatched value for developers.

Comments

Subscribe to join the conversation...

Be the first to comment

Enjoyed this article?

Get it daily. 7am. Free. Reads in 5 minutes.

Join 2,950 builders reading daily.

Also get