Navigate
AI BENCHY
Advertise here

Qwen3.6 Max Preview (medium) vs Qwen3.8 Max (low)

Qwen3.8 Max (low) leads on average score with 8.7 vs 8.4. Qwen3.8 Max (low) has the lower benchmark cost at $0.687 vs $1.129. Qwen3.8 Max (low) is faster at 21.19s vs 67.53s, with pass rates of 80.3% vs 84.9%.

Last updated at: 2026-08-04

Rank
#28
Total Output Tokens
169,940
Response Time (avg)
67.53s
Total Cost
$1.129
Rank
#23
Total Output Tokens
81,411
Response Time (avg)
21.19s
Total Cost
$0.687
Recommended model Qwen3.8 Max (low)

It has the best score here (8.7), while costing about 1.6x less than Qwen3.6 Max Preview (medium).

Detailed comparison

Metric Qwen3.6 Max Preview Qwen3.6 Max Preview medium Release: 2026-04-20 Qwen3.8 Max Qwen3.8 Max low Release: 2026-08-04
Score 8.4 8.7
Rank #28 #23
Reliability 9.9 10.0
Consistency 8.9 9.0
Benchmark coverage 22/22 tests · 66/66 attempts 22/22 tests · 66/66 attempts
Tests Correct
Attempt pass rate 80.3% 84.9%
Flaky tests 3 3
Total Runs 66 66
Cost per result 8.173 4.041
Total Cost $1.129 $0.687
Input Price $1.028 / 1M $2.000 / 1M
Output Price $6.162 / 1M $6.000 / 1M
Total Input Tokens 79,240 99,172
Output Tokens 5,098 6,132
Reasoning Tokens 164,842 75,279
Response Time (avg) 67.53s 21.19s
Response Time (max) 238.07s 155.75s
Response Time (total) 1485.64s 466.14s

Model generation showcase

Hamster playing table tennis

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

#28 Qwen3.6 Max Preview

medium
Cost
$0.024
Time
76.5s
Tokens
3,861 tok

#23 Qwen3.8 Max

low
Cost
$0.026
Time
68.5s
Tokens
4,280 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
Qwen3.6 Max Preview 8.8 7.8 88.9% 1 146.48s 7,895 427 52,957
Qwen3.8 Max 8.4 7.4 88.9% 1 28.69s 8,127 512 15,952

Quick Compare

Switch Comparison Pair