readable AI benchmarks

Google

Gemma 4 26B A4B (Non-reasoning)

non-reasoning · open weights · Apr 2, 2026

Quality Score15.0
Value Score20.2
Reliability18.8
Cache Discount4%

Model specification

Reasoning
non-reasoning
Input modalities
text, image, video
Output modalities
text
Context window
256k tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$0.130
Output
$0.400
Cached Input
$0.125
Cached Output
not available
Cost per task
not available

Capability

Intelligence
20.4
Coding
not available
Agentic
not available
Omniscience
-62.3
Correct
15.5%
Blended price
$0.154

Answer outcomes

Correct 15.5%Incorrect 77.8%Abstained 6.7%

Artificial Analysis benchmarks

SciCode
37%
Humanity’s Last Exam
11%
GPQA Diamond
71%
CritPt
0%
AA-Omniscience
19%
AA-LCR
41%

Similar models