readable AI benchmarks

IBM

Granite 4.1 8B

non-reasoning · open weights · Apr 29, 2026

Quality Score8.0
Value Score8.9
Reliability17.9
Cache Discountnot available

Model specification

Reasoning
non-reasoning
Input modalities
text
Output modalities
text
Context window
131,072 tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$0.050
Output
$0.100
Cached Input
not available
Cached Output
not available
Cost per task
not available

Capability

Intelligence
6.4
Coding
9.5
Agentic
not available
Omniscience
-64.1
Correct
12.3%
Blended price
$0.055

Answer outcomes

Correct 12.3%Incorrect 76.4%Abstained 11.3%

Artificial Analysis benchmarks

Terminal-Bench v2.1
3%
SciCode
22%
Humanity’s Last Exam
4%
GPQA Diamond
43%
CritPt
0%
AA-Omniscience
18%
AA-LCR
11%

Similar models