AI BENCHY
Advertise here
#133

MiniMax M2.7

Minimax Release: 2026-03-18 Tested on: 2026-05-21 23:52 minimax/minimax-m2.7::medium

Summary

MiniMax M2.7 scores 5.0 on AI BENCHY and ranks #133. It has 8.3 reliability, a 46.7% pass rate, $0.104 total cost, and 29.96s average response time.

What makes MiniMax M2.7 unique: It stands out most in Coding, where it ranks #1, while Instructions following is its weakest area at #15.

Score

5.0

Consistency

5.9

Reliability

8.3

Total Cost (Current Price)

$0.104

Total Output Tokens

81,525

Total Input Tokens

0

Input Price

$0.279 / 1M

Output Price

$1.200 / 1M

Tests Correct

Wrong Tests: 16

Attempt pass rate: 46.7%

Flaky tests

10

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

29.96s

Response Time (max): 117.04s

Response Time (total): 569.33s

Wrong answer: 7 Did not follow instructions: 5 Timed out: 2 Invalid tool call: 1 No answer: 1

Generation showcase

Hamster playing table tennis

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

#133 MiniMax M2.7

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

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-06-04 13:26 New test added 5.3 7.8 $0.124 ↓ Compare
2026-05-21 23:52 Suite changed 5.0 8.3 $0.104 Current run
2026-04-11 01:44 First recorded run 5.3 N/A $0.091 Compare

This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

MiniMax M2.7mediumvsQwen3.5-35B-A3BnoneMiniMax M2.7mediumvsGLM 5V TurbononeMiniMax M2.7mediumvsQwen3.6 FlashnoneMiniMax M2.7mediumvsQwen3.5 Plus 2026-02-15noneMiniMax M2.7mediumvsGLM 5noneMiniMax M2.7mediumvsGemini 3.5 FlashhighMiniMax M2.7mediumvsGemini 3 Flash PreviewmediumMiniMax M2.7mediumvsNemotron 3 Ultra 550b A55bmediumFree AvailableMiniMax M2.7mediumvsGPT-5.5low

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 7.9 6.3
Coding 6.7 9.6
Combined 4.7 1.6
Data parsing and extraction 6.3 5.8
Domain specific 3.0 10.0
General Intelligence 3.9 2.5
Instructions following 3.8 1.6
Puzzle Solving 3.5 4.4
Tool Calling 4.7 1.6
Trivia 3.0 10.0

Compared models