Navigate
Advertise here

Gemini 3.5 Flash Lite (high) vs Gemini 4 Argon (medium)

The average score is effectively tied at 9.0 vs 9.0. Gemini 3.5 Flash Lite (high) has the lower benchmark cost at $0.624 vs $0.674. Gemini 4 Argon (medium) is faster at 6.63s vs 11.92s, with pass rates of 84.1% vs 84.1%.

Last updated at: 2026-10-13

Compared models

Rank
#46
Total Output Tokens
219,926
Response Time (avg)
11.92s
Total Cost
$0.624
Rank
#47
Total Output Tokens
24,283
Response Time (avg)
6.63s
Total Cost
$0.674
Recommended model Gemini 4 Argon (medium)

It has the best score here (9.0), while responding about 1.8x faster than Gemini 3.5 Flash Lite (high).

Detailed comparison

Metric Gemini 3.5 Flash Lite Gemini 3.5 Flash Lite high Release: 2026-07-21 Gemini 4 Argon Gemini 4 Argon medium Release: 2026-10-13
Score 9.0 9.0
Rank #46 #47
Reliability 10.0 10.0
Consistency 9.3 9.6
Attempts 69/69 69/69
Tests Correct
Attempt pass rate 84.1% 84.1%
Flaky tests 2 1
Total Runs 69 69
Cost per result 3.463 3.545
Total Cost $0.624 $0.674
Input Price $0.300 / 1M $2.000 / 1M
Output Price $2.500 / 1M $10.000 / 1M
Cache Read Price $0.030 / 1M $0.100 / 1M
Cache Write Price $0.084 / 1M $0.188 / 1M
Total Input Tokens 244,529 215,326
Output Tokens 6,784 6,668
Reasoning Tokens 213,142 17,615
Response Time (avg) 11.92s 6.63s
Response Time (max) 53.09s 62.49s
Response Time (total) 274.14s 152.50s
Parameters ~150B total (~10B active) ~1.2T total (~20B active)
Availability Closed Closed

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.

#46 Gemini 3.5 Flash Lite

high
Cost
$0.025
Time
36.8s
Tokens
9,964 tok

#47 Gemini 4 Argon

medium
Cost
$0.053
Time
43.0s
Tokens
5,348 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 8.4 7.4 88.9% 1 16.58s 8,130 434 57,369
Gemini 4 Argon 10.0 10.0 100.0% 0 4.86s 8,448 506 4,391

Switch Comparison Pair