Navigate
AI BENCHY
Advertise here

Meituan: LongCat 2.0 vs Xiaomi: MiMo-V2.5

MiMo-V2.5 (medium) leads on average score with 6.5 vs 6.3. LongCat 2.0 has the lower benchmark cost at $0.044 vs $0.082. LongCat 2.0 is faster at 5.18s vs 32.20s, with pass rates of 36.4% vs 69.7%.

Recommended modelLongCat 2.0Its score stays close to the best score here (6.3 vs 6.5), while costing about 1.9x less than MiMo-V2.5 (medium).

Last updated at: 2026-07-21

Metric LongCat 2.0 LongCat 2.0 none Release: 2026-07-20 MiMo-V2.5 MiMo-V2.5 medium Release: 2026-04-22
Score 6.3 6.5
Rank #117 #107
Reliability 10.0 10.0
Consistency 9.3 7.9
Tests Correct
Attempt pass rate 36.4% 69.7%
Flaky tests 2 6
Total Runs 66 66
Cost per result 0.627 3.124
Total Cost $0.044 $0.082
Input Price $0.300 / 1M $0.140 / 1M
Output Price $1.200 / 1M $0.280 / 1M
Total Input Tokens 108,743 105,447
Output Tokens 9,372 7,120
Reasoning Tokens 0 230,682
Response Time (avg) 5.18s 32.20s
Response Time (max) 48.38s 162.44s
Response Time (total) 113.95s 708.46s

Hamster playing table tennis

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

#117 LongCat 2.0

none
Cost
$0.027
Time
411.7s
Tokens
22,283 tok

#107 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
LongCat 2.0 5.5 10.0 33.3% 0 2.85s 7,446 578 0
MiMo-V2.5 6.2 4.7 66.7% 2 97.14s 7,422 557 81,977

Quick Compare

Switch Comparison Pair