AI BENCHY
Advertise here
#61

Gemma 4 26B A4B

Google Release: 2026-04-03 Tested on: 2026-06-04 14:22 google/gemma-4-26b-a4b-it::medium
(medium) (none)

Summary

Gemma 4 26B A4B scores 7.2 on AI BENCHY and ranks #61. It has 10.0 reliability, a 69.8% pass rate, $0.045 total cost, and 63.41s average response time.

What makes Gemma 4 26B A4B unique: It stands out most in Instructions following, where it ranks #1, while Coding is its weakest area at #14.

Score

7.2

Consistency

9.2

Total Cost (Current Price)

$0.045 ↓ -12.8%

Tested at: $0.051

Total Output Tokens

128,490

Total Input Tokens

40,252

Input Price

$0.060 / 1M

Output Price

$0.330 / 1M

Tests Correct

Wrong Tests: 7

Attempt pass rate: 69.8%

Flaky tests

2

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

Response Time (avg)

63.41s

Response Time (max): 369.32s

Response Time (total): 1268.28s

Generation showcase

Hamster playing table tennis

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

#61 Gemma 4 26B A4B

medium
Invalid SVG
Cost
$0.000
Time
300.0s
Tokens
0 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-06-04 14:22 New test added 7.6 8.9 $0.045 Current run
2026-05-22 00:42 Suite changed 7.5 10.0 $0.045 Compare
2026-04-22 21:39 First recorded run 8.0 N/A $0.028 Compare

This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price
2026-06-04 15:40 $0.060 / 1M $0.330 / 1M

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

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 10.0 10.0
Coding 2.9 10.0
Combined 9.6 10.0
Data parsing and extraction 10.0 10.0
Domain specific 2.9 4.4
General Intelligence 10.0 10.0
Instructions following 10.0 10.0
Puzzle Solving 10.0 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models