Navigate
AI BENCHY
Advertise here

StepFun: Step 3.7 Flash vs Xiaomi: MiMo-V2.5-Pro

The average score is effectively tied at 6.9 vs 6.9. MiMo-V2.5-Pro (medium) has the lower benchmark cost at $0.187 vs $1.207. MiMo-V2.5-Pro (medium) is faster at 33.92s vs 64.68s, with pass rates of 63.6% vs 66.7%.

Recommended modelMiMo-V2.5-Pro (medium)It has the best score here (6.9), while costing about 6.5x less than Step 3.7 Flash (high).

Last updated at: 2026-07-21

Metric Step 3.7 Flash Step 3.7 Flash high Release: 2026-05-29 MiMo-V2.5-Pro MiMo-V2.5-Pro medium Release: 2026-04-22
Score 6.9 6.9
Rank #90 #88
Reliability 10.0 10.0
Consistency 8.0 8.2
Tests Correct
Attempt pass rate 63.6% 66.7%
Flaky tests 5 5
Total Runs 66 66
Cost per result 10.973 3.218
Total Cost $1.207 $0.187
Input Price $0.200 / 1M $0.435 / 1M
Output Price $1.150 / 1M $0.870 / 1M
Total Input Tokens 98,691 139,883
Output Tokens 1,032,395 15,521
Reasoning Tokens 0 130,992
Response Time (avg) 64.68s 33.92s
Response Time (max) 364.99s 197.54s
Response Time (total) 1423.01s 746.19s

Hamster playing table tennis

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

#90 Step 3.7 Flash

high
Cost
$0.007
Time
63.6s
Tokens
6,030 tok

#88 MiMo-V2.5-Pro

medium
Invalid SVG
Cost
$0.000
Time
300.0s
Tokens
0 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
Step 3.7 Flash 4.0 6.0 22.2% 1 206.21s 6,057 327,340 0
MiMo-V2.5-Pro 6.2 4.7 66.7% 2 92.07s 6,543 780 51,218

Quick Compare

Switch Comparison Pair