Navigate
AI BENCHY
Advertise here

Mistral Small 4 — medium vs none

The average score is effectively tied at 5.1 vs 5.1. none has the lower benchmark cost at $0.022 vs $0.096. none is faster at 1.20s vs 10.77s, with pass rates of 42.4% vs 25.8%.

Last updated at: 2026-07-28

Rank
#187
Total Output Tokens
131,824
Response Time (avg)
10.77s
Total Cost
$0.096
Rank
#185
Total Output Tokens
9,812
Response Time (avg)
1.20s
Total Cost
$0.022
Recommended model none

It has the best score here (5.1), while costing about 4.4x less than Mistral Small 4 (medium).

Detailed comparison

Metric Mistral Small 4 Mistral Small 4 medium Release: 2026-03-16 Mistral Small 4 Mistral Small 4 none Release: 2026-03-16
Score 5.1 5.1
Rank #187 #185
Reliability 10.0 10.0
Consistency 7.0 9.6
Tests Correct
Attempt pass rate 42.4% 25.8%
Flaky tests 8 1
Total Runs 66 66
Cost per result 1.913 0.432
Total Cost $0.096 $0.022
Input Price $0.150 / 1M $0.150 / 1M
Output Price $0.600 / 1M $0.600 / 1M
Total Input Tokens 140,494 104,708
Output Tokens 39,462 9,812
Reasoning Tokens 92,362 0
Response Time (avg) 10.77s 1.20s
Response Time (max) 59.15s 13.16s
Response Time (total) 236.94s 26.38s

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

#185 Mistral Small 4

none
Cost
$0.002
Time
10.4s
Tokens
2,370 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
Mistral Small 4 3.7 9.7 0.0% 0 901ms 7,636 619 0

Quick Compare

Switch Comparison Pair