Navigate
AI BENCHY
Advertise here

Gemma 4 26B A4B (medium) vs Step 3.7 Flash (high)

Step 3.7 Flash (high) leads on average score with 6.9 vs 6.6. Gemma 4 26B A4B (medium) has the lower benchmark cost at $0.096 vs $1.207. Step 3.7 Flash (high) is faster at 64.68s vs 103.83s, with pass rates of 66.7% vs 63.6%.

Last updated at: 2026-07-25

Rank
#104
Total Output Tokens
247,527
Response Time (avg)
103.83s
Total Cost
$0.096
Rank
#94
Total Output Tokens
1,032,395
Response Time (avg)
64.68s
Total Cost
$1.207
Recommended model Gemma 4 26B A4B (medium)

Its score stays close to the best score here (6.6 vs 6.9), while costing about 12.7x less than Step 3.7 Flash (high).

Detailed comparison

Metric Gemma 4 26B A4B Gemma 4 26B A4B medium Release: 2026-04-03 Free Available Step 3.7 Flash Step 3.7 Flash high Release: 2026-05-29
Score 6.6 6.9
Rank #104 #94
Reliability 9.4 10.0
Consistency 9.2 8.0
Tests Correct
Attempt pass rate 66.7% 63.6%
Flaky tests 2 5
Total Runs 66 66
Cost per result 0.643 10.973
Total Cost $0.096 $1.207
Input Price $0.120 / 1M $0.200 / 1M
Output Price $0.350 / 1M $1.150 / 1M
Total Input Tokens 77,550 98,691
Output Tokens 28,036 1,032,395
Reasoning Tokens 219,491 0
Response Time (avg) 103.83s 64.68s
Response Time (max) 912.19s 364.99s
Response Time (total) 2180.47s 1423.01s

Hamster playing table tennis

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

#104 Gemma 4 26B A4B

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

#94 Step 3.7 Flash

high
Cost
$0.007
Time
63.6s
Tokens
6,030 tok

Top Models by Score

Score vs Total Cost

Response Time (avg)

Score vs Response Time (avg)

Total Output Tokens

Score vs Total Output Tokens

Category Breakdown

Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Gemma 4 26B A4B 2.9 10.0 0.0% 0 272.54s 5,062 14,838 44,567
Step 3.7 Flash 4.0 6.0 22.2% 1 206.21s 6,057 327,340 0

Quick Compare

Switch Comparison Pair