Navigate
AI BENCHY
Advertise here

Google: Gemini 3.1 Pro Preview vs OpenAI: GPT-5.3-Codex

Gemini 3.1 Pro Preview (medium) leads on average score with 9.2 vs 8.9. GPT-5.3-Codex (medium) has the lower benchmark cost at $0.920 vs $1.361. GPT-5.3-Codex (medium) is faster at 16.96s vs 21.47s, with pass rates of 90.9% vs 83.3%.

Recommended modelGPT-5.3-Codex (medium)It offers the best overall trade-off: a competitive score (8.9), lower cost than Gemini 3.1 Pro Preview (medium), and balanced response time.

Last updated at: 2026-07-25

Metric Gemini 3.1 Pro Preview Gemini 3.1 Pro Preview medium Release: 2026-02-19 GPT-5.3-Codex GPT-5.3-Codex medium Release: 2026-02-05
Score 9.2 8.9
Rank #10 #18
Reliability 10.0 10.0
Consistency 10.0 8.6
Tests Correct
Attempt pass rate 90.9% 83.3%
Flaky tests 0 4
Total Runs 66 66
Cost per result 6.801 5.748
Total Cost $1.361 $0.920
Input Price $2.000 / 1M $1.750 / 1M
Output Price $12.000 / 1M $14.000 / 1M
Total Input Tokens 92,287 81,268
Output Tokens 5,232 6,251
Reasoning Tokens 92,726 49,274
Response Time (avg) 21.47s 16.96s
Response Time (max) 88.68s 100.93s
Response Time (total) 322.08s 373.19s

Hamster playing table tennis

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

#10 Gemini 3.1 Pro Preview

medium
Cost
$0.115
Time
87.2s
Tokens
9,629 tok

#18 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 Pro Preview 7.9 9.9 66.7% 0 40.17s 8,124 435 41,247
GPT-5.3-Codex 10.0 10.0 100.0% 0 19.50s 7,302 535 10,890

Quick Compare

Switch Comparison Pair