AI BENCHY
Advertise here
#53

MiMo-V2.5

Xiaomi Release: 2026-04-22 Tested on: 2026-05-22 12:59 xiaomi/mimo-v2.5::medium
(medium) (none)

Summary

MiMo-V2.5 scores 7.4 on AI BENCHY and ranks #53. It has 10.0 reliability, a 70.0% pass rate, $0.346 total cost, and 20.40s average response time.

Score

7.4

Consistency

8.4

Reliability

10.0

Total Cost (Current Price)

$0.346

Total Output Tokens

164,736

Total Input Tokens

0

Input Price

$0.400 / 1M

Output Price

$2.000 / 1M

Tests Correct

Wrong Tests: 8

Attempt pass rate: 70.0%

Flaky tests

4

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

Response Time (avg)

20.40s

Response Time (max): 97.49s

Response Time (total): 407.98s

Wrong answer: 4 Extra formatting: 2 Did not follow instructions: 1 No answer: 1

Generation showcase

Hamster playing table tennis

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

#53 MiMo-V2.5

medium
Cost
$0.002
Time
54.8s
Tokens
5,247 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-06-04 13:56 New test added 7.3 10.0 $0.063 ↓ Compare
2026-05-22 12:59 New test added 7.4 10.0 $0.346 Current run
2026-05-08 15:28 Suite changed 7.8 10.0 $0.253 Compare
2026-04-22 22:54 First recorded run 7.8 N/A $0.253 Compare

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

Run comparison

RunScoreConsistencyReliabilityTests CorrectFlaky testsTotal Output TokensTotal Input TokensTotal CostResponse Time (avg)
2026-05-22 12:59 · New test added7.48.410.012/204164,7360$0.34620.40s
2026-05-08 15:28 · Suite changed7.88.610.012/183119,0280$0.25314.40s
Difference-0.4-0.20.00+1+457080+$0.094+5999ms

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

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-V2.5mediumvsGemini 3 Flash PreviewnoneMiMo-V2.5mediumvsGemini 3.1 Flash Lite PreviewlowMiMo-V2.5mediumvsGrok Build 0.1mediumMiMo-V2.5mediumvsQwen3.6 35B A3BmediumMiMo-V2.5mediumvsClaude Sonnet 4.6mediumMiMo-V2.5mediumvsGemini 3 Flash PreviewmediumMiMo-V2.5mediumvsGemini 3.5 FlashhighMiMo-V2.5mediumvsNemotron 3 Ultra 550b A55bmediumFree AvailableMiMo-V2.5mediumvsGemini 3.5 Flashlow

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 10.0 10.0
Coding 6.9 6.2
Combined 10.0 10.0
Data parsing and extraction 2.7 5.7
Domain specific 5.3 10.0
General Intelligence 5.4 2.5
Instructions following 9.9 10.0
Puzzle Solving 8.2 7.2
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models