AI BENCHY
Advertise here
#46

Grok Build 0.1

X AI Release: 2026-05-21 Tested on: 2026-05-22 00:36 x-ai/grok-build-0.1::medium
(medium) (none)

Summary

Grok Build 0.1 scores 7.6 on AI BENCHY and ranks #46. It has 10.0 reliability, a 70.0% pass rate, $0.633 total cost, and 26.36s average response time.

What makes Grok Build 0.1 unique: It stands out most in Domain specific, 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.

Score

7.6

Consistency

8.5

Reliability

10.0

Total Cost (Current Price)

$0.633

Total Output Tokens

295,603

Total Input Tokens

0

Input Price

$1.000 / 1M

Output Price

$2.000 / 1M

Tests Correct

Wrong Tests: 8

Attempt pass rate: 70.0%

Flaky tests

4

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

Response Time (avg)

26.36s

Response Time (max): 103.89s

Response Time (total): 527.19s

Wrong answer: 4 Extra formatting: 2 Did not follow instructions: 2

Generation showcase

Hamster playing table tennis

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

#46 xAI: Grok Build 0.1

medium
Cost
$0.028
Time
81.3s
Tokens
14,009 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-06-04 14:22 New test added 7.4 10.0 $0.927 Compare
2026-05-26 13:30 Re-test 7.7 10.0 $0.729 Compare
2026-05-22 00:36 Suite changed 7.6 10.0 $0.633 Current run

This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.

Run comparison

RunScoreConsistencyReliabilityTests CorrectFlaky testsTotal Output TokensTotal Input TokensTotal CostResponse Time (avg)
2026-05-22 00:36 · Suite changed7.68.510.012/204295,6030$0.63326.36s
2026-06-04 14:22 · New test added7.49.910.013/210440,80044,418$0.92749.90s
Difference+0.2-1.40.0-1+4-145197-44418-$0.294-23542ms

These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.

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 Build 0.1mediumvsMiniMax M3mediumGrok Build 0.1mediumvsStep 3.7 FlashlowGrok Build 0.1mediumvsKimi K2.5mediumGrok Build 0.1mediumvsClaude Opus 4.6mediumGrok Build 0.1mediumvsMercury 2mediumGrok Build 0.1mediumvsGemini 3.5 FlashhighGrok Build 0.1mediumvsGemini 3 Flash PreviewmediumGrok Build 0.1mediumvsNemotron 3 Ultra 550b A55bmediumFree AvailableGrok Build 0.1mediumvsGPT-5.5low

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 10.0 10.0
Coding 5.3 2.9
Combined 10.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 5.3 10.0
General Intelligence 3.8 2.5
Instructions following 9.8 10.0
Puzzle Solving 6.2 7.5
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models