#106 SpaceXAI: Grok 4.7
xhigh- Cost
- $0.235
- Time
- 544.2s
- Tokens
- 39,247 tok
X AI
Release: 2026-09-21
Tested on: 2026-09-21 22:00
x-ai/grok-4.7::xhigh
~1.7T total (~170B active)MoEClosedEstimated
Summary
Grok 4.7 scores 7.5 on AI BENCHY and ranks #106. It has 9.6 reliability, a 77.3% pass rate, $2.625 total cost, and 115.74s average response time.
What makes Grok 4.7 unique: It stands out most in Anti-AI Tricks, where it ranks #3, while Coding is its weakest area at #16. It uses unusually many reasoning tokens, which can help explain its slower or more expensive runs.
Model facts
Researched on 2026-09-21
- Parameters
- ~1.7T total (~170B active)
- Architecture
- MoE
- Availability
- Closed
- License
- -
Best estimate from public evidence; the vendor did not disclose every value. Exact API checkpoint is closed. Parameter counts and MoE architecture remain low-confidence estimates carried from the curated Grok 4 family baseline, not vendor disclosures for Grok 4.7.
7.5
Consistency
7.7
9.6
$2.625
Total Output Tokens
505,069
Total Input Tokens
124,896
Input Price
$1.600 / 1M
Output Price
$4.800 / 1M
Flaky tests
6
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
Charts
Choose the first model, then click a second model to open a side-by-side page.
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
Grok 4.7xhighvsClaude Opus 5noneGrok 4.7xhighvsGPT-5.4 NanomediumGrok 4.7xhighvsNemotron 3 UltramediumFree AvailableGrok 4.7xhighvsGPT-5.6 TerralowGrok 4.7xhighvsSolar Pro 4xhighGrok 4.7xhighvsGrok 4.7highGrok 4.7xhighvsGPT-5.6 LunahighGrok 4.7xhighvsMiniMax M3mediumGrok 4.7xhighvsDeepSeek V4 Flash 0423highGrok 4.7xhighvsGPT 5.3 Chatnone
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 8.7 | 7.9 | |
| Coding | 5.3 | 4.5 | |
| Combined | 10.0 | 10.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 3.5 | 4.4 | |
| General Intelligence | 4.7 | 1.6 | |
| Instructions following | 9.8 | 10.0 | |
| Puzzle Solving | 10.0 | 10.0 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |