Advertise here
#109

Grok 4.7

X AI Release: 2026-09-21 Tested on: 2026-09-21 22:04 x-ai/grok-4.7::high
~1.7T total (~170B active)MoEClosedEstimated
(xhigh) (high) (medium) (low)

Summary

Grok 4.7 scores 7.5 on AI BENCHY and ranks #109. It has 9.5 reliability, a 75.8% pass rate, $2.180 total cost, and 113.10s average response time.

What makes Grok 4.7 unique: It stands out most in Anti-AI Tricks, where it ranks #4, while General Intelligence is its weakest area at #15.

Model facts

Researched on 2026-09-21

Estimated
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.

Parameter source 1 Parameter source 2 Availability source

Score

7.5

Consistency

7.6

Reliability

9.5

Total Cost (Current Price)

$2.180

Total Output Tokens

416,086

Total Input Tokens

113,892

Input Price

$1.600 / 1M

Output Price

$4.800 / 1M

Tests Correct

Wrong Tests: 9

Attempt pass rate: 75.8%

Flaky tests

7

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

113.10s

Response Time (max): 573.57s

Response Time (total): 2488.20s

No answer: 3 Did not follow instructions: 2 Wrong answer: 2 API error: 1 Invalid tool call: 1

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#109 SpaceXAI: Grok 4.7

high
Cost
$0.110
Time
301.3s
Tokens
23,143 tok

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Grok 4.7highvsGPT-5.6 TerralowGrok 4.7highvsMiniMax M3mediumGrok 4.7highvsGPT-5.4 NanomediumGrok 4.7highvsGPT 5.3 ChatnoneGrok 4.7highvsGrok 4.7xhighGrok 4.7highvsQwen3.5 Plus 2026-02-15mediumGrok 4.7highvsClaude Opus 5noneGrok 4.7highvsQwen3.5-27BmediumGrok 4.7highvsNemotron 3 UltramediumFree AvailableGrok 4.7highvsMercury 2.5 Previewmedium

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 8.7 7.9
Coding 6.0 4.6
Combined 8.6 6.9
Data parsing and extraction 10.0 10.0
Domain specific 5.3 7.2
General Intelligence 4.1 2.7
Instructions following 8.4 6.9
Puzzle Solving 10.0 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models