Navigate
AI BENCHY
AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com

Gemini 3.5 Flash Lite (high) vs GPT-5.3-Codex (medium)

GPT-5.3-Codex (medium) leads on average score with 8.9 vs 8.8. Gemini 3.5 Flash Lite (high) has the lower benchmark cost at $0.200 vs $0.920. Gemini 3.5 Flash Lite (high) is faster at 10.84s vs 16.96s, with pass rates of 86.4% vs 83.3%.

Last updated at: 2026-08-01

Rank
#21
Total Output Tokens
75,922
Response Time (avg)
10.84s
Total Cost
$0.200
Rank
#19
Total Output Tokens
55,525
Response Time (avg)
16.96s
Total Cost
$0.920
Recommended model Gemini 3.5 Flash Lite (high)

Its score stays close to the best score here (8.8 vs 8.9), while costing about 4.6x less than GPT-5.3-Codex (medium).

Detailed comparison

Metric Gemini 3.5 Flash Lite Gemini 3.5 Flash Lite high Release: 2026-07-21 GPT-5.3-Codex GPT-5.3-Codex medium Release: 2026-02-05
Score 8.8 8.9
Rank #21 #19
Reliability 10.0 10.0
Consistency 10.0 8.6
Tests Correct
Attempt pass rate 86.4% 83.3%
Flaky tests 0 4
Total Runs 22 66
Cost per result 1.048 5.748
Total Cost $0.200 $0.920
Input Price $0.300 / 1M $1.750 / 1M
Output Price $2.500 / 1M $14.000 / 1M
Total Input Tokens 30,858 81,268
Output Tokens 2,072 6,251
Reasoning Tokens 73,850 49,274
Response Time (avg) 10.84s 16.96s
Response Time (max) 50.65s 100.93s
Response Time (total) 238.40s 373.19s

Model generation showcase

Hamster playing table tennis

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

#21 Gemini 3.5 Flash Lite

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

#19 GPT-5.3-Codex

medium
Cost
$0.049
Time
54.9s
Tokens
3,580 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 7.8 10.0 66.7% 0 15.51s 2,712 143 19,439
GPT-5.3-Codex 10.0 10.0 100.0% 0 19.50s 7,302 535 10,890

Quick Compare

Switch Comparison Pair