Navigate
Advertise here

Gemini 3.5 Flash Lite (medium) vs Step 3.7 Flash (low)

Gemini 3.5 Flash Lite (medium) leads on average score with 7.3 vs 7.2. Gemini 3.5 Flash Lite (medium) has the lower benchmark cost at $0.440 vs $0.449. Gemini 3.5 Flash Lite (medium) is faster at 8.68s vs 20.72s, with pass rates of 76.8% vs 63.8%.

Last updated at: 2026-10-01

Compared models

Rank
#138
Total Output Tokens
129,214
Response Time (avg)
8.68s
Total Cost
$0.440
Rank
#147
Total Output Tokens
339,108
Response Time (avg)
20.72s
Total Cost
$0.449
Recommended model Gemini 3.5 Flash Lite (medium)

It has the best score here (7.3), while responding about 2.4x faster than Step 3.7 Flash (low).

Detailed comparison

Metric Gemini 3.5 Flash Lite Gemini 3.5 Flash Lite medium Release: 2026-07-21 Step 3.7 Flash Step 3.7 Flash low Release: 2026-05-29
Score 7.3 7.2
Rank #138 #147
Reliability 10.0 10.0
Consistency 7.6 7.9
Attempts 69/69 69/69
Tests Correct
Attempt pass rate 76.8% 63.8%
Flaky tests 7 6
Total Runs 69 69
Cost per result 3.140 4.078
Total Cost $0.440 $0.449
Input Price $0.300 / 1M $0.200 / 1M
Output Price $2.500 / 1M $1.150 / 1M
Cache Read Price $0.030 / 1M $0.040 / 1M
Cache Write Price $0.084 / 1M N/A
Total Input Tokens 388,307 292,685
Output Tokens 10,412 339,108
Reasoning Tokens 118,802 0
Response Time (avg) 8.68s 20.72s
Response Time (max) 86.92s 124.75s
Response Time (total) 199.65s 476.67s
Parameters ~150B total (~10B active) 198B total (11B active)
Availability Closed Open source

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Model generation showcase

Hamster playing table tennis

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

#138 Gemini 3.5 Flash Lite

medium
Cost
$0.010
Time
17.8s
Tokens
4,000 tok

#147 Step 3.7 Flash

low
Invalid SVG
Cost
$0.004
Time
25.3s
Tokens
3,072 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
Gemini 3.5 Flash Lite 7.9 9.9 66.7% 0 9.96s 8,122 471 28,930
Step 3.7 Flash 8.2 7.2 88.9% 1 9.46s 7,437 18,685 0

Quick Compare

Switch Comparison Pair