Navigate
AI BENCHY
Advertise here

Mistral Small 4 (medium) vs GPT-4o-mini

Mistral Small 4 (medium) leads on average score with 5.1 vs 5.0. GPT-4o-mini has the lower benchmark cost at $0.010 vs $0.096. GPT-4o-mini is faster at 1.99s vs 10.77s, with pass rates of 42.4% vs 22.7%.

Last updated at: 2026-07-28

Rank
#187
Total Output Tokens
131,824
Response Time (avg)
10.77s
Total Cost
$0.096
Rank
#195
Total Output Tokens
2,911
Response Time (avg)
1.99s
Total Cost
$0.010
Recommended model GPT-4o-mini

Its score stays close to the best score here (5.0 vs 5.1), while costing about 9.8x less than Mistral Small 4 (medium).

Detailed comparison

Metric Mistral Small 4 Mistral Small 4 medium Release: 2026-03-16 GPT-4o-mini GPT-4o-mini none Release: 2024-07-18
Score 5.1 5.0
Rank #187 #195
Reliability 10.0 10.0
Consistency 7.0 9.9
Tests Correct
Attempt pass rate 42.4% 22.7%
Flaky tests 8 0
Total Runs 66 66
Cost per result 1.913 0.195
Total Cost $0.096 $0.010
Input Price $0.150 / 1M $0.150 / 1M
Output Price $0.600 / 1M $0.600 / 1M
Total Input Tokens 140,494 53,136
Output Tokens 39,462 2,911
Reasoning Tokens 92,362 0
Response Time (avg) 10.77s 1.99s
Response Time (max) 59.15s 7.58s
Response Time (total) 236.94s 29.86s

Model generation showcase

Hamster playing table tennis

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

#187 Mistral Small 4

medium
Cost
$0.006
Time
47.9s
Tokens
9,857 tok

#195 GPT-4o-mini

none
Cost
$0.001
Time
6.6s
Tokens
742 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
Mistral Small 4 4.4 5.1 33.3% 2 39.98s 7,636 11,635 54,715
GPT-4o-mini 3.2 9.6 0.0% 0 1.63s 7,314 367 0

Quick Compare

Switch Comparison Pair