Navigate
AI BENCHY
Advertise here

DeepSeek V4 Flash 0731 (high) vs GPT-5 Mini (medium)

GPT-5 Mini (medium) leads on average score with 8.1 vs 8.0. DeepSeek V4 Flash 0731 (high) has the lower benchmark cost at $0.123 vs $0.237. GPT-5 Mini (medium) is faster at 27.63s vs 110.77s, with pass rates of 78.8% vs 63.6%.

Last updated at: 2026-08-01

Rank
#40
Total Output Tokens
544,164
Response Time (avg)
110.77s
Total Cost
$0.123
Rank
#33
Total Output Tokens
105,932
Response Time (avg)
27.63s
Total Cost
$0.237
Recommended model GPT-5 Mini (medium)

It has the best score here (8.1), while responding about 4.0x faster than DeepSeek V4 Flash 0731 (high).

Detailed comparison

Metric DeepSeek V4 Flash 0731 DeepSeek V4 Flash 0731 high Release: 2026-08-01 GPT-5 Mini GPT-5 Mini medium Release: 2025-08-07
Score 8.0 8.1
Rank #40 #33
Reliability 9.6 10.0
Consistency 7.8 8.8
Tests Correct
Attempt pass rate 78.8% 63.6%
Flaky tests 6 3
Total Runs 66 66
Cost per result 0.878 1.971
Total Cost $0.123 $0.237
Input Price $0.140 / 1M $0.250 / 1M
Output Price $0.280 / 1M $2.000 / 1M
Total Input Tokens 96,609 98,374
Output Tokens 32,924 14,434
Reasoning Tokens 511,240 91,498
Response Time (avg) 110.77s 27.63s
Response Time (max) 600.61s 111.48s
Response Time (total) 2437.00s 607.92s

Model generation showcase

Hamster playing table tennis

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

#40 DeepSeek V4 Flash 0731

high
Invalid SVG
Cost
$0.000
Time
187.3s
Tokens
19,048 tok

#33 GPT-5 Mini

medium
Cost
$0.007
Time
42.9s
Tokens
3,432 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 V4 Flash 0731 6.3 4.2 77.8% 2 252.67s 7,044 2,160 191,210
GPT-5 Mini 10.0 10.0 100.0% 0 27.63s 7,302 658 17,152

Quick Compare

Switch Comparison Pair