AI BENCHY
Advertise here
#153

Granite 4.1 8B

IBM Granite Release: 2026-05-01 Tested on: 2026-05-22 00:30 ibm-granite/granite-4.1-8b::none

Summary

Granite 4.1 8B scores 4.1 on AI BENCHY and ranks #153. It has 10.0 reliability, a 10.0% pass rate, $0.003 total cost, and 723ms average response time.

What makes Granite 4.1 8B unique: It stands out most in Coding, where it ranks #3, while Instructions following is its weakest area at #13. It is notably fast compared with similar models.

Score

4.1

Consistency

10.0

Reliability

10.0

Total Cost (Current Price)

$0.003

Total Output Tokens

2,742

Total Input Tokens

0

Input Price

$0.050 / 1M

Output Price

$0.100 / 1M

Tests Correct

Wrong Tests: 18

Attempt pass rate: 10.0%

Flaky tests

0

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

Response Time (avg)

723ms

Response Time (max): 2.17s

Response Time (total): 14.45s

Wrong answer: 12 Did not follow instructions: 5 Invalid tool call: 1

Generation showcase

Hamster playing table tennis

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

#153 IBM: Granite 4.1 8B

none
Cost
$0.001
Time
3.2s
Tokens
491 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-06-04 14:07 New test added 4.0 10.0 $0.003 Compare
2026-05-22 00:30 Suite changed 4.1 10.0 $0.003 Current run
2026-05-01 00:31 Initial run 4.3 10.0 $0.003 Compare

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 00:30 · Suite changed4.110.010.02/2002,7420$0.003723ms
2026-05-01 00:31 · Initial run4.310.010.02/1802,7120$0.003767ms
Difference-0.20.00.000+300+$0.001-44ms

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

Granite 4.1 8BnonevsGrok 4.20noneGranite 4.1 8BnonevsQwen3.5-122B-A10BnoneGranite 4.1 8BnonevsDeepSeek V3.2noneGranite 4.1 8BnonevsGLM 5 TurbononeGranite 4.1 8BnonevsMiniMax M2.7mediumGranite 4.1 8BnonevsGemini 3.5 FlashhighGranite 4.1 8BnonevsGemini 3 Flash PreviewmediumGranite 4.1 8BnonevsNemotron 3 Ultra 550b A55bmediumFree AvailableGranite 4.1 8BnonevsGPT-5.5low

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 4.9 10.0
Coding 5.2 10.0
Combined 3.0 10.0
Data parsing and extraction 3.0 10.0
Domain specific 3.0 10.0
General Intelligence 4.0 10.0
Instructions following 3.6 9.9
Puzzle Solving 3.2 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models