Navigate
AI BENCHY
Advertise here

Kimi K2.5 (medium) vs Step 3.7 Flash (low)

Step 3.7 Flash (low) leads on average score with 7.3 vs 7.0. Step 3.7 Flash (low) has the lower benchmark cost at $0.454 vs $0.600. Step 3.7 Flash (low) is faster at 20.68s vs 99.00s, with pass rates of 65.2% vs 68.2%.

Last updated at: 2026-07-28

Rank
#87
Total Output Tokens
227,367
Response Time (avg)
99.00s
Total Cost
$0.600
Rank
#77
Total Output Tokens
376,581
Response Time (avg)
20.68s
Total Cost
$0.454
Recommended model Step 3.7 Flash (low)

It has the best score here (7.3), while responding about 4.8x faster than Kimi K2.5 (medium).

Detailed comparison

Metric Kimi K2.5 Kimi K2.5 medium Release: 2026-01-27 Step 3.7 Flash Step 3.7 Flash low Release: 2026-05-29
Score 7.0 7.3
Rank #87 #77
Reliability 10.0 10.0
Consistency 7.0 8.1
Tests Correct
Attempt pass rate 65.2% 68.2%
Flaky tests 8 5
Total Runs 66 66
Cost per result 4.789 3.782
Total Cost $0.600 $0.454
Input Price $0.571 / 1M $0.200 / 1M
Output Price $2.850 / 1M $1.150 / 1M
Total Input Tokens 118,448 103,833
Output Tokens 62,124 376,581
Reasoning Tokens 165,243 0
Response Time (avg) 99.00s 20.68s
Response Time (max) 281.00s 124.75s
Response Time (total) 1485.04s 455.01s

Model generation showcase

Hamster playing table tennis

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

#87 MoonshotAI: Kimi K2.5

medium
Cost
$0.030
Time
58.6s
Tokens
8,683 tok

#77 Step 3.7 Flash

low
Invalid SVG
Cost
$0.004
Time
25.3s
Tokens
3,072 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
Kimi K2.5 6.1 4.6 66.7% 2 217.49s 6,935 5,705 74,693
Step 3.7 Flash 8.2 7.2 88.9% 1 9.46s 7,437 18,685 0

Quick Compare

Switch Comparison Pair