Navigate
AI BENCHY
Advertise here

DeepSeek: DeepSeek V4 Flash vs Xiaomi: MiMo-V2.5-Pro

DeepSeek V4 Flash leads on average score with 5.6 vs 5.5. DeepSeek V4 Flash has the lower benchmark cost at $0.044 vs $0.068. MiMo-V2.5-Pro is faster at 4.12s vs 36.78s, with pass rates of 31.8% vs 37.9%.

Recommended modelMiMo-V2.5-ProIts score stays close to the best score here (5.5 vs 5.6), while responding about 8.9x faster than DeepSeek V4 Flash.

Last updated at: 2026-07-22

Metric DeepSeek V4 Flash DeepSeek V4 Flash none Release: 2026-04-24 MiMo-V2.5-Pro MiMo-V2.5-Pro none Release: 2026-04-22
Score 5.6 5.5
Rank #156 #160
Reliability 10.0 10.0
Consistency 8.5 8.6
Tests Correct
Attempt pass rate 31.8% 37.9%
Flaky tests 4 4
Total Runs 66 66
Cost per result 0.917 1.509
Total Cost $0.044 $0.068
Input Price $0.098 / 1M $0.435 / 1M
Output Price $0.196 / 1M $0.870 / 1M
Total Input Tokens 240,221 124,799
Output Tokens 100,727 15,362
Reasoning Tokens 0 0
Response Time (avg) 36.78s 4.12s
Response Time (max) 247.27s 53.13s
Response Time (total) 809.09s 90.55s

Hamster playing table tennis

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

#156 DeepSeek V4 Flash

none
Cost
$0.004
Time
157.6s
Tokens
11,297 tok

#160 MiMo-V2.5-Pro

none
Cost
$0.004
Time
46.4s
Tokens
4,025 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
DeepSeek V4 Flash 4.2 7.4 11.1% 1 17.13s 7,279 9,717 0
MiMo-V2.5-Pro 4.3 7.8 22.2% 1 1.41s 6,559 485 0

Quick Compare

Switch Comparison Pair