Navigate
AI BENCHY
Advertise here

AI BENCHY Compare

Kwaipilot: KAT-Coder-Pro V2.5 vs Xiaomi: MiMo-V2.5

Summary

KAT-Coder-Pro V2.5 leads on average score with 6.8 vs 6.7. MiMo-V2.5 (medium) has the lower benchmark cost at $0.061 vs $0.220. KAT-Coder-Pro V2.5 is faster at 10.81s vs 27.11s, with pass rates of 71.4% vs 69.8%.

Recommended modelMiMo-V2.5 (medium)Its score stays close to the best score here (6.7 vs 6.8), while costing about 3.6x less than KAT-Coder-Pro V2.5.

Last updated at: 2026-07-14

Metric KAT-Coder-Pro V2.5 KAT-Coder-Pro V2.5 none Release: 2026-07-14 MiMo-V2.5 MiMo-V2.5 medium Release: 2026-04-22
Score 6.8 6.7
Rank #89 #94
Reliability 10.0 10.0
Consistency 7.3 8.1
Tests Correct
Attempt pass rate 71.4% 69.8%
Flaky tests 7 5
Total Runs 63 63
Cost per result 1.992 2.966
Total Cost $0.220 $0.061
Input Price $0.740 / 1M $0.105 / 1M
Output Price $2.960 / 1M $0.280 / 1M
Total Input Tokens 42,749 41,838
Output Tokens 63,338 2,827
Reasoning Tokens 0 198,898
Response Time (avg) 10.81s 27.11s
Response Time (max) 53.57s 162.44s
Response Time (total) 227.02s 569.38s

Generation showcase

Hamster playing table tennis

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

#89 KAT-Coder-Pro V2.5

none
Cost
$0.010
Time
29.0s
Tokens
3,439 tok

#94 MiMo-V2.5

medium
Cost
$0.002
Time
54.8s
Tokens
5,247 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
KAT-Coder-Pro V2.5 6.1 4.7 66.7% 2 22.52s 7,893 22,440 0
MiMo-V2.5 6.2 4.7 66.7% 2 97.14s 7,422 557 81,977

Quick Compare

Switch Comparison Pair