Navigate
AI BENCHY
Advertise here

DeepSeek V3.2 (medium) vs GPT-5.5

The average score is effectively tied at 7.0 vs 7.0. DeepSeek V3.2 (medium) has the lower benchmark cost at $0.078 vs $0.544. GPT-5.5 is faster at 2.35s vs 68.43s, with pass rates of 65.2% vs 59.1%.

Last updated at: 2026-08-15

Rank
#116
Total Output Tokens
128,787
Response Time (avg)
68.43s
Total Cost
$0.078
Rank
#118
Total Output Tokens
4,915
Response Time (avg)
2.35s
Total Cost
$0.544
Recommended model DeepSeek V3.2 (medium)

It has the best score here (7.0), while costing about 7.1x less than GPT-5.5.

Detailed comparison

Metric DeepSeek V3.2 DeepSeek V3.2 medium Release: 2025-12-01 GPT-5.5 GPT-5.5 none Release: 2026-04-24
Score 7.0 7.0
Rank #116 #118
Reliability 10.0 10.0
Consistency 7.4 9.2
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 65.2% 59.1%
Flaky tests 7 2
Total Runs 66 66
Cost per result 0.672 4.533
Total Cost $0.078 $0.544
Input Price $0.269 / 1M $5.000 / 1M
Output Price $0.400 / 1M $30.000 / 1M
Total Input Tokens 101,056 79,294
Output Tokens 11,832 4,915
Reasoning Tokens 116,955 0
Response Time (avg) 68.43s 2.35s
Response Time (max) 376.10s 12.24s
Response Time (total) 1505.53s 51.78s
Parameters 671B total (37B active) ~1.5T total (~100B active)
Availability Open source Closed

Model generation showcase

Hamster playing table tennis

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

#116 DeepSeek V3.2

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

#118 GPT-5.5

none
Cost
$0.090
Time
54.3s
Tokens
3,063 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 5.5 10.0 33.3% 0 1.35s 7,305 462 0

Quick Compare

Switch Comparison Pair