Navigate
AI BENCHY
Advertise here

Qwen3.7 Max (medium) vs Qwen3.8 Max (medium)

The average score is effectively tied at 9.2 vs 9.1. Qwen3.8 Max (medium) has the lower benchmark cost at $0.728 vs $1.116. Qwen3.8 Max (medium) is faster at 21.53s vs 40.57s, with pass rates of 87.9% vs 84.9%.

Last updated at: 2026-08-04

Rank
#12
Total Output Tokens
216,752
Response Time (avg)
40.57s
Total Cost
$1.116
Rank
#14
Total Output Tokens
84,826
Response Time (avg)
21.53s
Total Cost
$0.728
Recommended model Qwen3.8 Max (medium)

It has the best score here (9.1), while costing about 1.5x less than Qwen3.7 Max (medium).

Detailed comparison

Metric Qwen3.7 Max Qwen3.7 Max medium Release: 2026-05-22 Qwen3.8 Max Qwen3.8 Max medium Release: 2026-08-04
Score 9.2 9.1
Rank #12 #14
Reliability 10.0 10.0
Consistency 9.3 9.7
Benchmark coverage 22/22 tests · 66/66 attempts 22/22 tests · 66/66 attempts
Tests Correct
Attempt pass rate 87.9% 84.9%
Flaky tests 2 1
Total Runs 66 66
Cost per result 8.292 4.040
Total Cost $1.116 $0.728
Input Price $1.475 / 1M $2.000 / 1M
Output Price $4.425 / 1M $6.000 / 1M
Total Input Tokens 106,020 109,046
Output Tokens 5,748 6,567
Reasoning Tokens 211,004 78,259
Response Time (avg) 40.57s 21.53s
Response Time (max) 556.06s 126.60s
Response Time (total) 892.57s 473.75s

Model generation showcase

Hamster playing table tennis

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

#12 Qwen3.7 Max

medium
Cost
$0.017
Time
68.8s
Tokens
4,526 tok

#14 Qwen3.8 Max

medium
Cost
$0.028
Time
71.9s
Tokens
4,750 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
Qwen3.7 Max 10.0 10.0 100.0% 0 35.31s 7,893 423 34,808
Qwen3.8 Max 10.0 10.0 100.0% 0 41.35s 7,893 430 23,804

Quick Compare

Switch Comparison Pair