#243 IBM: Granite 4.2 8B
medium
Provider returned error
- Cost
- $0.000
- Time
- 0.2s
- Tokens
- 0 tok
IBM Granite
Release: 2026-09-02
Tested on: 2026-09-02 02:10
ibm-granite/granite-4.2-8b::medium
8BDenseOpen source
Summary
Granite 4.2 8B scores 5.2 on AI BENCHY and ranks #243. It has 8.7 reliability, a 34.9% pass rate, $0.009 total cost, and 45.97s average response time.
What makes Granite 4.2 8B unique: It stands out most in Anti-AI Tricks, where it ranks #1, while Instructions following is its weakest area at #14.
Model facts
Researched on 2026-09-02
- 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.
5.2
Consistency
9.6
8.7
$0.009
Total Output Tokens
19,330
Total Input Tokens
52,909
Input Price
$0.100 / 1M
Output Price
$0.150 / 1M
Flaky tests
1
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
Granite 4.2 8BmediumvsInklingnoneGranite 4.2 8BmediumvsNemotron 3.5 LightningmediumFree AvailableGranite 4.2 8BmediumvsDots 3 Note PreviewnoneFree AvailableGranite 4.2 8BmediumvsMistral Small 4noneGranite 4.2 8BmediumvsQwen3.6 35B A3BnoneGranite 4.2 8BmediumvsMistral Small 4mediumGranite 4.2 8BmediumvsLing-2.6-1TnoneGranite 4.2 8BmediumvsGranite 4.2 8BlowGranite 4.2 8BmediumvsSeed-2.0-CodenoneGranite 4.2 8BmediumvsQwen3 Coder Nextnone
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| 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 |