Navigate
AI BENCHY
Advertise here

AI BENCHY Compare

DeepSeek: DeepSeek V3.2 vs OpenAI: GPT-5.5

Summary

GPT-5.5 (low) leads on average score with 9.3 vs 7.0. DeepSeek V3.2 (medium) has the lower benchmark cost at $0.078 vs $1.253. GPT-5.5 (low) is faster at 10.13s vs 68.62s, with pass rates of 65.2% vs 86.4%.

Recommended modelGPT-5.5 (low)It has the best score here (9.3), while responding about 6.8x faster than DeepSeek V3.2 (medium).

Last updated at: 2026-07-16

Metric DeepSeek V3.2 DeepSeek V3.2 medium Release: 2025-12-01 GPT-5.5 GPT-5.5 low Release: 2026-04-24
Score 7.0 9.3
Rank #72 #6
Reliability 10.0 10.0
Consistency 7.4 10.0
Tests Correct
Attempt pass rate 65.2% 86.4%
Flaky tests 7 0
Total Runs 66 66
Cost per result 0.671 6.594
Total Cost $0.078 $1.253
Input Price $0.269 / 1M $5.000 / 1M
Output Price $0.400 / 1M $30.000 / 1M
Total Input Tokens 101,047 80,058
Output Tokens 11,834 5,378
Reasoning Tokens 117,014 23,040
Response Time (avg) 68.62s 10.13s
Response Time (max) 376.10s 56.19s
Response Time (total) 1509.53s 222.82s

Generation showcase

Hamster playing table tennis

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

#72 DeepSeek V3.2

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

#6 GPT-5.5

low
Cost
$0.068
Time
37.0s
Tokens
2,339 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-5.5 10.0 10.0 100.0% 0 15.04s 7,302 423 6,402

Quick Compare

Switch Comparison Pair