Advertise here
#248

MiMo-V2.5-Pro

Xiaomi Release: 2026-04-22 Tested on: 2026-10-01 02:09 xiaomi/mimo-v2.5-pro::medium
1.02T total (42B active)MoEOpen source
(medium) (none)

Summary

MiMo-V2.5-Pro scores 6.4 on AI BENCHY and ranks #248. It has 10.0 reliability, a 63.8% pass rate, $0.332 total cost, and 56.72s average response time.

What makes MiMo-V2.5-Pro unique: It stands out most in Coding, where it ranks #3, while Domain specific is its weakest area at #14.

Model facts

Researched on 2026-08-12

Reported
Parameters
1.02T total (42B active)
Architecture
MoE
Availability
Open source
License
MIT
Parameter source Availability source

Score

6.4

Consistency

7.6

Reliability

10.0

Total Cost (Current Price)

$0.332 ↓ -33.9%

Tested at: $0.502

Total Output Tokens

223,971

Total Input Tokens

253,462

Input Price

$0.435 / 1M

Output Price

$0.870 / 1M

Cache Read Price

$0.004 / 1M

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: 12

Attempt pass rate: 63.8%

Flaky tests

7

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

Response Time (avg)

56.72s

Response Time (max): 333.34s

Response Time (total): 1304.54s

Wrong answer: 4 Extra formatting: 3 Did not follow instructions: 2 API error: 1 Invalid tool call: 1 No answer: 1

Hamster playing table tennis

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

#248 MiMo-V2.5-Pro

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

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-10-01 02:09 Re-test 6.4 10.0 $0.332 ↓ Current run
2026-07-16 22:50 New test added 6.9 10.0 $0.187 ↓ Compare
2026-06-04 13:52 New test added 7.5 10.0 $0.106 ↓ Compare
2026-05-08 15:28 Suite changed 8.1 10.0 $0.200 Compare
2026-04-22 22:54 First recorded run 8.1 N/A $0.201 Compare

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

Run comparison

RunBenchmark coverageScoreConsistencyReliabilityTests CorrectFlaky testsTotal Output TokensTotal Input TokensTotal CostResponse Time (avg)
2026-10-01 02:09 · Current run69/69 attempts6.47.610.011/237223,971253,462$0.33256.72s
2026-07-16 22:50 · New test added66/66 attempts6.98.210.012/225146,513139,883$0.18733.92s
Difference—-0.5-0.60.0-1+2+77458+113579+$0.145+22801ms

Benchmark coverage differs: 69/69 attempts (Target: 3 repeats per test) versus 66/66 attempts (Target: 3 repeats per test). Totals and repeat-sensitive metrics are not directly comparable.

These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price Cache Read Price Cache Write Price
2026-08-14 12:51 $0.435 / 1M $0.870 / 1M N/A N/A
2026-10-01 18:33 $0.435 / 1M $0.870 / 1M $0.004 / 1M N/A

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

MiMo-V2.5-PromediumvsGemini 3.5 FlashminimalMiMo-V2.5-PromediumvsDots 3 Note PreviewhighFree AvailableMiMo-V2.5-PromediumvsMercury 2.5mediumMiMo-V2.5-PromediumvsDots 3 Note PreviewlowFree AvailableMiMo-V2.5-PromediumvsBeam 1.0 501B A23BlowMiMo-V2.5-PromediumvsLongCat 2.0noneMiMo-V2.5-PromediumvsKimi K2.5mediumMiMo-V2.5-PromediumvsQwen3.5-35B-A3BmediumMiMo-V2.5-PromediumvsMinimax M3.1 FlashxhighFree AvailableMiMo-V2.5-PromediumvsQwen3.6 27Bnone

Category Breakdown

Category Score Consistency Tests Correct
Agentic 4.7 1.6
Anti-AI Tricks 10.0 10.0
Coding 6.2 4.7
Combined 6.9 5.9
Data parsing and extraction 7.3 5.8
Domain specific 2.9 7.2
General Intelligence 5.5 10.0
Instructions following 9.9 10.0
Puzzle Solving 6.7 7.9
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models