Navigate
AI BENCHY
Advertise here

DeepSeek V4 Flash 0731 vs Mistral Small 4 (medium)

DeepSeek V4 Flash 0731 leads on average score with 5.4 vs 5.1. DeepSeek V4 Flash 0731 has the lower benchmark cost at $0.021 vs $0.096. Mistral Small 4 (medium) is faster at 10.77s vs 20.70s, with pass rates of 27.3% vs 42.4%.

Last updated at: 2026-08-01

Rank
#182
Total Output Tokens
25,424
Response Time (avg)
20.70s
Total Cost
$0.021
Rank
#191
Total Output Tokens
131,824
Response Time (avg)
10.77s
Total Cost
$0.096
Recommended model DeepSeek V4 Flash 0731

It has the best score here (5.4), while costing about 4.7x less than Mistral Small 4 (medium).

Detailed comparison

Metric DeepSeek V4 Flash 0731 DeepSeek V4 Flash 0731 none Release: 2026-08-01 Mistral Small 4 Mistral Small 4 medium Release: 2026-03-16
Score 5.4 5.1
Rank #182 #191
Reliability 10.0 10.0
Consistency 8.6 7.0
Tests Correct
Attempt pass rate 27.3% 42.4%
Flaky tests 4 8
Total Runs 66 66
Cost per result 0.509 1.913
Total Cost $0.021 $0.096
Input Price $0.140 / 1M $0.150 / 1M
Output Price $0.280 / 1M $0.600 / 1M
Total Input Tokens 94,557 140,494
Output Tokens 25,424 39,462
Reasoning Tokens 0 92,362
Response Time (avg) 20.70s 10.77s
Response Time (max) 387.15s 59.15s
Response Time (total) 455.38s 236.94s

Model generation showcase

Hamster playing table tennis

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

#182 DeepSeek V4 Flash 0731

none
Cost
$0.004
Time
198.4s
Tokens
14,316 tok

#191 Mistral Small 4

medium
Cost
$0.006
Time
47.9s
Tokens
9,857 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 4.3 10.0 0.0% 0 1.72s 7,275 505 0
Mistral Small 4 4.4 5.1 33.3% 2 39.98s 7,636 11,635 54,715

Quick Compare

Switch Comparison Pair