readable AI benchmarks

Google

DiffusionGemma 26B A4B

reasoning · open weights · Jun 10, 2026

Quality Score13.9
Value Scorenot available
Reliability20.4
Cache Discountnot available

Model specification

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

Token prices USD per 1M tokens

Input
not available
Output
not available
Cached Input
not available
Cached Output
not available
Cost per task
not available

Capability

Intelligence
13.5
Coding
19.7
Agentic
not available
Omniscience
-59.2
Correct
16.6%
Blended price
not available

Answer outcomes

Correct 16.6%Incorrect 75.8%Abstained 7.6%

Artificial Analysis benchmarks

GDPval-AA v2
3%
Terminal-Bench v2.1
12%
SciCode
34%
Humanity’s Last Exam
11%
GPQA Diamond
67%
CritPt
0%
AA-Omniscience
20%
AA-LCR
18%

Similar models