xAI
Grok 4.6
xAI's cost-efficient frontier model, posting frontier-level composite index results at $2/$6 per million tokens.
Our editorial assessment, based on the public sources listed below. Last reviewed .
- Overall rank
- #28
- Tier
- A
- Score
- 83.2
- Main category
- Overall
Strengths
- Frontier-level composite intelligence at low $2/$6 pricing
- Completes long agentic tasks in roughly half the turns of rivals
- Strong cost-per-task value for reasoning-heavy work
Considerations
- Peak scores trail the very top Claude and GPT flagships
- Weights are proprietary with no self-host option
Price
$2 / $6 per 1M tokens (in/out)
Shown for reference — price is not part of the score.
Score breakdown
- Performance
- 86.0
- 55% of score
- Reputation
- 82.0
- 35% of score
- Recency
- 72.0
- 10% of score
The overall score combines these sub-scores using the weights shown. How we score →
Verification status
Each field carries its own re-verification date. Amber means older than 90 days — treat those figures as stale until re-checked.
Checked against the sources listed below.
Sources
- xAI — Grok 4.7 announcement (successor) (opens in a new tab)Accessed:
- Artificial Analysis — LLM Leaderboard (opens in a new tab)Accessed:
- 15 Frontier AI Models Worth Watching 2026 (opens in a new tab)Accessed:
- Swfte AI Model Leaderboard (Sep 2026) (opens in a new tab)Accessed:
- xAI Docs — Models and pricing (opens in a new tab)Accessed:
Similar models
- Grok 4.5xAI#24 · Tier A · Score 83.8Compare
- MiMo-V2.6-ProXiaomi#25 · Tier A · Score 83.8Compare
- Mistral Large 4Mistral AI#36 · Tier A · Score 81.8Compare
- Qwen 3.7 MaxAlibaba#38 · Tier A · Score 81.7Compare