Advertise here
#228

Minimax M3.1 Flash

Minimax Release: 2026-10-19 Tested on: 2026-10-19 16:17 minimax/minimax-m3.1-flash::high
-OtherClosed

Summary

Minimax M3.1 Flash scores 6.5 on AI BENCHY and ranks #228. It has 10.0 reliability, a 56.5% pass rate, $0.000 total cost, and 34.00s average response time.

What makes Minimax M3.1 Flash unique: It stands out most in Combined, where it ranks #1, while Instructions following is its weakest area at #17. Its total benchmark cost is unusually low for its score range.

Identity note

Space Bunny Alpha was the preview version of Minimax M3.1 Flash.

Model facts

Researched on 2026-10-19

Parameters
-
Architecture
Other
Availability
Closed
License
-

MiniMax officially released M3.1 Flash on October 19 and says model weights will be released later. This exact API checkpoint is closed. The announcement describes increased sparsity but does not disclose parameter counts or a sufficient exact architecture specification; no unsupported numeric estimate is assigned. Space Bunny was an early version, not proof of identical checkpoint weights. Retain its historical measurements separately. The exact free route declares mandatory low, medium, high, xhigh and max reasoning efforts. Its MiniMax endpoint reports training=false with prompt retention; use existing OpenRouter account guardrails.

Score

6.5

Consistency

7.2

Total Output Tokens

279,438

Total Input Tokens

357,984

Input Price

$0.000 / 1M

Output Price

$0.000 / 1M

Cache Read Price

N/A

Cache Write Price

N/A

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

Tests Correct

Wrong Tests: 14

Attempt pass rate: 56.5%

Flaky tests

8

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

Response Time (avg)

34.00s

Response Time (max): 280.72s

Response Time (total): 781.92s

Hamster playing table tennis

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

#228 Minimax M3.1 Flash

high
Cost
$0.000
Time
75.4s
Tokens
9,436 tok

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

Category Breakdown

Category Score Consistency Tests Correct
Agentic 6.1 3.1
Anti-AI Tricks 6.4 7.9
Coding 5.6 4.7
Combined 10.0 10.0
Data parsing and extraction 6.5 10.0
Domain specific 5.9 7.2
General Intelligence 4.6 9.8
Instructions following 5.3 2.6
Puzzle Solving 6.0 7.1
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models