Navigate
Advertise here

MiniMax M3 (medium) vs Qwen3.7 Max

The average score is effectively tied at 7.5 vs 7.4. Qwen3.7 Max has the lower benchmark cost at $0.197 vs $0.300. Qwen3.7 Max is faster at 4.56s vs 75.15s, with pass rates of 62.1% vs 68.2%.

Last updated at: 2026-09-10

Compared models

Rank
#104
Total Output Tokens
275,782
Response Time (avg)
75.15s
Total Cost
$0.300
Rank
#113
Total Output Tokens
12,446
Response Time (avg)
4.56s
Total Cost
$0.197
Recommended model Qwen3.7 Max

It has the best score here (7.4), while costing about 1.5x less than MiniMax M3 (medium).

Detailed comparison

Metric MiniMax M3 MiniMax M3 medium Release: 2026-06-01 Qwen3.7 Max Qwen3.7 Max none Release: 2026-05-22
Score 7.5 7.4
Rank #104 #113
Reliability 9.7 9.9
Consistency 8.0 10.0
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 62.1% 68.2%
Flaky tests 5 0
Total Runs 66 66
Cost per result 2.724 1.581
Total Cost $0.300 $0.197
Input Price $0.300 / 1M $1.475 / 1M
Output Price $1.200 / 1M $4.425 / 1M
Total Input Tokens 121,996 95,992
Output Tokens 90,051 12,446
Reasoning Tokens 185,731 0
Response Time (avg) 75.15s 4.56s
Response Time (max) 431.03s 72.30s
Response Time (total) 1578.24s 100.30s
Parameters 428B total (23B active) ~1T total (~40B active)
Availability Weights available Closed

Model generation showcase

Hamster playing table tennis

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

#104 MiniMax M3

medium
Cost
$0.012
Time
154.4s
Tokens
10,018 tok

#113 Qwen3.7 Max

none
Cost
$0.046
Time
195.0s
Tokens
12,171 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
MiniMax M3 6.1 6.5 55.6% 1 144.74s 5,804 6,223 32,667
Qwen3.7 Max 5.5 10.0 33.3% 0 1.35s 7,911 582 0

Quick Compare

Switch Comparison Pair