Advertise here
#272

Granite 4.2 8B

IBM Granite Release: 2026-09-02 Tested on: 2026-10-01 04:34 ibm-granite/granite-4.2-8b::medium
8BDenseOpen source
(high) (medium) (low) (none)

Summary

Granite 4.2 8B scores 6.1 on AI BENCHY and ranks #272. It has 8.9 reliability, a 37.7% pass rate, $0.029 total cost, and 50.47s average response time.

What makes Granite 4.2 8B unique: It stands out most in Agentic, where it ranks #1, while Instructions following is its weakest area at #16.

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

6.1

Consistency

9.7

Reliability

8.9

Total Cost (Current Price)

$0.029

Total Output Tokens

50,045

Total Input Tokens

259,708

Input Price

$0.060 / 1M

Output Price

$0.250 / 1M

Cache Read Price

$0.015 / 1M

Cache Write Price

N/A

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Tests Correct

Wrong Tests: 15

Attempt pass rate: 37.7%

Flaky tests

1

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

Response Time (avg)

50.47s

Response Time (max): 557.96s

Response Time (total): 1160.91s

Wrong answer: 9 Timed out: 4 Did not follow instructions: 1 No answer: 1

Hamster playing table tennis

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

#272 IBM: Granite 4.2 8B

medium
Provider returned error
Cost
$0.000
Time
0.2s
Tokens
0 tok

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price Cache Read Price Cache Write Price
2026-10-01 18:33 $0.060 / 1M $0.250 / 1M $0.015 / 1M N/A

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 8BmediumvsStep 5 PreviewmediumGranite 4.2 8BmediumvsKAT-Coder-Pro V2.5defaultGranite 4.2 8BmediumvsQwen3.5 Plus 2026-04-20noneGranite 4.2 8BmediumvsApodex 1.1 MinimediumFree AvailableGranite 4.2 8BmediumvsInklingnoneFree AvailableGranite 4.2 8BmediumvsGLM 5.3 FlashXlowGranite 4.2 8BmediumvsApodex 1.1 MinilowFree AvailableGranite 4.2 8BmediumvsMiMo-V2.6-PrononeGranite 4.2 8BmediumvsTrinity Large ThinkingmediumGranite 4.2 8BmediumvsInkling SmallmediumFree Available

Category Breakdown

Category Score Consistency Tests Correct
Agentic 10.0 10.0
Anti-AI Tricks 8.4 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 3.8 6.0
Puzzle Solving 3.1 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models