Navigate
AI BENCHY
Advertise here

AI BENCHY Compare

DeepSeek: DeepSeek V3.2 vs OpenAI: GPT-5.4 Nano

Summary

GPT-5.4 Nano (medium) leads on average score with 7.5 vs 7.0. DeepSeek V3.2 (medium) has the lower benchmark cost at $0.078 vs $0.138. GPT-5.4 Nano (medium) is faster at 13.24s vs 68.62s, with pass rates of 65.2% vs 65.2%.

Recommended modelGPT-5.4 Nano (medium)It has the best score here (7.5), while responding about 5.2x faster than DeepSeek V3.2 (medium).

Last updated at: 2026-07-17

Metric DeepSeek V3.2 DeepSeek V3.2 medium Release: 2025-12-01 GPT-5.4 Nano GPT-5.4 Nano medium Release: 2026-03-17
Score 7.0 7.5
Rank #73 #51
Reliability 10.0 10.0
Consistency 7.4 8.5
Tests Correct
Attempt pass rate 65.2% 65.2%
Flaky tests 7 4
Total Runs 66 66
Cost per result 0.671 1.150
Total Cost $0.078 $0.138
Input Price $0.269 / 1M $0.200 / 1M
Output Price $0.400 / 1M $1.250 / 1M
Total Input Tokens 101,047 82,819
Output Tokens 11,834 7,100
Reasoning Tokens 117,014 90,022
Response Time (avg) 68.62s 13.24s
Response Time (max) 376.10s 94.06s
Response Time (total) 1509.53s 291.33s

Generation showcase

Hamster playing table tennis

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

#73 DeepSeek V3.2

medium
Cost
$0.001
Time
53.6s
Tokens
1,932 tok

#51 GPT-5.4 Nano

medium
Cost
$0.007
Time
24.6s
Tokens
4,943 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
DeepSeek V3.2 6.0 7.2 55.6% 1 248.68s 5,717 649 52,014
GPT-5.4 Nano 6.1 4.7 66.7% 2 19.12s 7,305 516 20,778

Quick Compare

Switch Comparison Pair