Navigate
Advertise here

Gemini 4 Carbon (medium) vs GPT-5.3-Codex (medium)

The average score is effectively tied at 9.1 vs 9.1. GPT-5.3-Codex (medium) has the lower benchmark cost at $1.318 vs $1.933. GPT-5.3-Codex (medium) is faster at 18.87s vs 38.78s, with pass rates of 95.7% vs 84.1%.

Last updated at: 2026-11-22

Compared models

Rank
#61
Total Output Tokens
131,948
Response Time (avg)
38.78s
Total Cost
$1.933
Rank
#63
Total Output Tokens
66,287
Response Time (avg)
18.87s
Total Cost
$1.318
Recommended model GPT-5.3-Codex (medium)

It has the best score here (9.1), while responding about 2.1x faster than Gemini 4 Carbon (medium).

Detailed comparison

Metric Gemini 4 Carbon Gemini 4 Carbon medium Release: 2026-11-12 GPT-5.3-Codex GPT-5.3-Codex medium Release: 2026-02-05
Score 9.1 9.1
Rank #61 #63
Reliability 8.8 10.0
Consistency 8.9 8.6
Attempts 69/69 69/69
Tests Correct
Attempt pass rate 95.7% 84.1%
Flaky tests 3 4
Total Runs 69 69
Cost per result 9.662 7.753
Total Cost $1.933 $1.318
Input Price $2.000 / 1M $1.750 / 1M
Output Price $10.000 / 1M $14.000 / 1M
Cache Read Price $0.100 / 1M $0.175 / 1M
Cache Write Price $0.188 / 1M N/A
Total Input Tokens 306,396 222,794
Output Tokens 5,746 7,357
Reasoning Tokens 126,202 58,930
Response Time (avg) 38.78s 18.87s
Response Time (max) 206.61s 100.93s
Response Time (total) 892.02s 433.94s
Parameters ~1.2T total (~20B active) ~1.2T total (~80B 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.

#61 Gemini 4 Carbon

medium
Cost
$0.203
Time
336.6s
Tokens
20,353 tok

#63 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 4 Carbon 10.0 10.0 100.0% 0 29.67s 8,448 487 17,950
GPT-5.3-Codex 10.0 10.0 100.0% 0 19.50s 7,302 535 10,890

Switch Comparison Pair