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

Compared models

Gemini 3.1 Flash Lite Preview (high) vs Gemini 3.1 Flash Lite Preview (medium) vs GPT-5.3-Codex (medium) benchmark comparison: GPT-5.3-Codex (medium) leads on Score with 8.9. Gemini 3.1 Flash Lite Preview (medium) leads on Reliability with 10.0. Gemini 3.1 Flash Lite Preview (medium) has the lowest Total Cost at $0.117. Gemini 3.1 Flash Lite Preview (medium) is fastest at 4.59s.

Last updated at: 2026-08-26

Rank
#233
Total Output Tokens
1,534,593
Response Time (avg)
68.14s
Total Cost
$2.310
Rank
#91
Total Output Tokens
57,778
Response Time (avg)
4.59s
Total Cost
$0.117
Rank
#22
Total Output Tokens
60,374
Response Time (avg)
16.91s
Total Cost
$0.988
Recommended model Gemini 3.1 Flash Lite Preview (medium)

It offers the best overall trade-off: a competitive score (7.4), lower cost than the other models in this comparison, and balanced response time.

Detailed comparison

Metric Gemini 3.1 Flash Lite Preview Gemini 3.1 Flash Lite Preview high Release: 2026-03-03 Gemini 3.1 Flash Lite Preview Gemini 3.1 Flash Lite Preview medium Release: 2026-03-03 GPT-5.3-Codex GPT-5.3-Codex medium Release: 2026-02-05
Score 5.3 7.4 8.9
Rank #233 #91 #22
Reliability N/A 10.0 10.0
Consistency 7.3 9.9 8.6
Attempts 48/66 66/66 66/66
Tests Correct
Attempt pass rate 59.1% 63.6% 83.3%
Flaky tests 0 0 4
Total Runs 48 66 66
Cost per result 17.763 0.829 6.171
Total Cost $2.310 $0.117 $0.988
Input Price $0.250 / 1M $0.250 / 1M $1.750 / 1M
Output Price $1.500 / 1M $1.500 / 1M $14.000 / 1M
Total Input Tokens 28,980 117,493 81,187
Output Tokens 1,283 10,589 6,258
Reasoning Tokens 1,533,310 47,189 54,116
Response Time (avg) 68.14s 4.59s 16.91s
Response Time (max) 280.52s 18.34s 100.93s
Response Time (total) 1090.28s 101.04s 372.03s
Parameters ~150B total (~10B active) ~150B total (~10B active) ~1.2T total (~80B active)
Availability Closed Closed Closed

Model generation showcase

Hamster playing table tennis

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

#233 Gemini 3.1 Flash Lite Preview

high
Cost
$0.096
Time
133.9s
Tokens
63,687 tok

#91 Gemini 3.1 Flash Lite Preview

medium
Cost
$0.003
Time
5.2s
Tokens
1,944 tok

#22 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 3.1 Flash Lite Preview 0.0 0.0 0.0% 0 0ms 0 0 0
Gemini 3.1 Flash Lite Preview 5.5 10.0 33.3% 0 4.09s 8,126 461 8,597
GPT-5.3-Codex 10.0 10.0 100.0% 0 19.50s 7,302 535 10,890

Quick Compare

Switch Comparison Pair