Navigate
Advertise here

MiniMax M2.7 (medium) vs MiniMax M3 (medium)

MiniMax M3 (medium) leads on average score with 6.7 vs 5.0. MiniMax M2.7 (medium) has the lower benchmark cost at $0.326 vs $0.422. MiniMax M2.7 (medium) is faster at 50.32s vs 77.03s, with pass rates of 44.9% vs 59.4%.

Last updated at: 2026-10-05

Compared models

Rank
#310
Total Output Tokens
174,351
Response Time (avg)
50.32s
Total Cost
$0.326
Rank
#185
Total Output Tokens
324,934
Response Time (avg)
77.03s
Total Cost
$0.422
Recommended model MiniMax M3 (medium)

It has the strongest score in this comparison (6.7) and the best overall balance of cost and response time across all 2 models.

Detailed comparison

Metric MiniMax M2.7 MiniMax M2.7 medium Release: 2026-03-18 MiniMax M3 MiniMax M3 medium Release: 2026-06-01
Score 5.0 6.7
Rank #310 #185
Reliability 10.0 9.7
Consistency 6.4 8.1
Attempts 69/69 69/69
Tests Correct
Attempt pass rate 44.9% 59.4%
Flaky tests 10 5
Total Runs 69 69
Cost per result 5.279 3.381
Total Cost $0.326 $0.422
Input Price $0.210 / 1M $0.300 / 1M
Output Price $0.840 / 1M $1.200 / 1M
Cache Read Price $0.042 / 1M $0.060 / 1M
Cache Write Price N/A N/A
Total Input Tokens 277,130 166,517
Output Tokens 45,188 107,386
Reasoning Tokens 129,163 217,548
Response Time (avg) 50.32s 77.03s
Response Time (max) 198.82s 431.03s
Response Time (total) 1107.03s 1694.74s
Parameters 230B total (10B active) 428B total (23B active)
Availability Weights available Weights available

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.

#310 MiniMax M2.7

medium
Cost
$0.022
Time
22.8s
Tokens
9,250 tok

#185 MiniMax M3

medium
Cost
$0.012
Time
154.4s
Tokens
10,018 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 M2.7 5.7 9.1 33.3% 0 101.89s 2,961 1,231 38,841
MiniMax M3 6.1 6.5 55.6% 1 144.74s 5,804 6,223 32,667

Quick Compare

Switch Comparison Pair