Navigate
AI BENCHY
Advertise here

Mistral Small 4 (medium) vs GPT-5.6 Luna

GPT-5.6 Luna leads on average score with 5.4 vs 5.1. GPT-5.6 Luna has the lower benchmark cost at $0.029 vs $0.097. GPT-5.6 Luna is faster at 1.50s vs 10.80s, with pass rates of 43.9% vs 36.4%.

Last updated at: 2026-08-20

Rank
#236
Total Output Tokens
133,597
Response Time (avg)
10.80s
Total Cost
$0.097
Rank
#221
Total Output Tokens
6,709
Response Time (avg)
1.50s
Total Cost
$0.029
Recommended model GPT-5.6 Luna

It has the best score here (5.4), while costing about 3.4x less than Mistral Small 4 (medium).

Detailed comparison

Metric Mistral Small 4 Mistral Small 4 medium Release: 2026-03-16 GPT-5.6 Luna GPT-5.6 Luna none Release: 2026-07-09
Score 5.1 5.4
Rank #236 #221
Reliability 10.0 10.0
Consistency 7.0 8.8
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 43.9% 36.4%
Flaky tests 8 3
Total Runs 66 66
Cost per result 1.923 2.357
Total Cost $0.097 $0.029
Input Price $0.150 / 1M $0.200 / 1M
Output Price $0.600 / 1M $1.200 / 1M
Total Input Tokens 140,559 101,332
Output Tokens 40,268 6,709
Reasoning Tokens 93,329 0
Response Time (avg) 10.80s 1.50s
Response Time (max) 59.15s 10.57s
Response Time (total) 237.60s 33.05s
Parameters 119B total (6B active) ~400B total (~17B active)
Availability Open source Closed

Model generation showcase

Hamster playing table tennis

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

#236 Mistral Small 4

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

#221 GPT-5.6 Luna

none
Cost
$0.016
Time
15.8s
Tokens
2,685 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-5.6 Luna 3.8 7.2 22.2% 1 980ms 7,302 459 0

Quick Compare

Switch Comparison Pair