Navigate
Advertise here

MiniMax M2.5 (medium) vs Qwen3.5-9B (medium)

MiniMax M2.5 (medium) leads on average score with 4.3 vs 4.0. Qwen3.5-9B (medium) has the lower benchmark cost at $0.106 vs $0.440. MiniMax M2.5 (medium) is faster at 102.32s vs 110.18s, with pass rates of 42.0% vs 26.1%.

Last updated at: 2026-10-03

Compared models

Rank
#348
Total Output Tokens
290,496
Response Time (avg)
102.32s
Total Cost
$0.440
Rank
#354
Total Output Tokens
458,993
Response Time (avg)
110.18s
Total Cost
$0.106
Recommended model Qwen3.5-9B (medium)

Its score stays close to the best score here (4.0 vs 4.3), while costing about 4.2x less than MiniMax M2.5 (medium).

Detailed comparison

Metric MiniMax M2.5 MiniMax M2.5 medium Release: 2026-02-12 Qwen3.5-9B Qwen3.5-9B medium Release: 2026-03-02
Score 4.3 4.0
Rank #348 #354
Reliability 9.3 8.7
Consistency 6.8 7.9
Attempts 69/69 69/69
Tests Correct
Attempt pass rate 42.0% 26.1%
Flaky tests 9 6
Total Runs 69 69
Cost per result 7.104 3.523
Total Cost $0.440 $0.106
Input Price $0.270 / 1M $0.100 / 1M
Output Price $1.080 / 1M $0.150 / 1M
Cache Read Price $0.027 / 1M N/A
Cache Write Price N/A N/A
Total Input Tokens 188,239 387,323
Output Tokens 27,822 48,562
Reasoning Tokens 262,674 410,431
Response Time (avg) 102.32s 110.18s
Response Time (max) 600.81s 569.97s
Response Time (total) 1637.05s 1873.00s
Parameters 230B total (10B active) 9B
Availability Weights available Open source

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Model generation showcase

Hamster playing table tennis

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

#348 MiniMax M2.5

medium
Reached the allocated time limit (300 seconds) without receiving showcase output.
Cost
$0.000
Time
300.0s
Tokens
0 tok

#354 Qwen3.5-9B

medium
Cost
$0.001
Time
35.9s
Tokens
3,030 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 M2.5 3.4 9.1 0.0% 0 188.58s 6,076 357 106,177
Qwen3.5-9B 2.9 10.0 0.0% 0 100.88s 2,396 7,890 41,129

Quick Compare

Switch Comparison Pair