AI BENCHY
Advertise here
#247

Granite 4.2 8B

IBM Granite Release: 2026-09-02 Tested on: 2026-09-02 02:14 ibm-granite/granite-4.2-8b::low
8BDenseOpen source
(high) (medium) (low) (none)

Summary

Granite 4.2 8B scores 5.1 on AI BENCHY and ranks #247. It has 9.0 reliability, a 31.8% pass rate, $0.012 total cost, and 54.36s average response time.

What makes Granite 4.2 8B unique: It stands out most in Anti-AI Tricks, where it ranks #2, while Instructions following is its weakest area at #15.

Model facts

Researched on 2026-09-02

Reported
Parameters
8B
Architecture
Dense
Availability
Open source
License
Apache-2.0

IBM publishes the weights, runnable implementation guidance, and training methodology under Apache-2.0.

Parameter source Availability source

Score

5.1

Consistency

10.0

Reliability

9.0

Total Cost (Current Price)

$0.012

Total Output Tokens

27,928

Total Input Tokens

74,721

Input Price

$0.100 / 1M

Output Price

$0.150 / 1M

Tests Correct

Wrong Tests: 15

Attempt pass rate: 31.8%

Flaky tests

0

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

Response Time (avg)

54.36s

Response Time (max): 566.80s

Response Time (total): 1195.97s

Wrong answer: 10 Timed out: 3 Did not follow instructions: 1 No answer: 1

Hamster playing table tennis

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

#247 IBM: Granite 4.2 8B

low
Provider returned error
Cost
$0.000
Time
0.2s
Tokens
0 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

Granite 4.2 8BlowvsMistral Small 4mediumGranite 4.2 8BlowvsQwen3 Coder NextnoneGranite 4.2 8BlowvsMistral Small 4noneGranite 4.2 8BlowvsMiMo-V2.5noneGranite 4.2 8BlowvsNemotron 3.5 LightningmediumFree AvailableGranite 4.2 8BlowvsQwen3.5-9BnoneGranite 4.2 8BlowvsGranite 4.2 8BmediumGranite 4.2 8BlowvsNorth Mini CodenoneFree AvailableGranite 4.2 8BlowvsInklingnoneGranite 4.2 8BlowvsMiniMax M2.7medium

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 8.3 10.0
Coding 5.5 10.0
Combined 3.0 10.0
Data parsing and extraction 6.5 10.0
Domain specific 5.3 10.0
General Intelligence 4.0 10.0
Instructions following 3.0 10.0
Puzzle Solving 3.0 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models