Navigate
Advertise here

Kimi K2.5 (medium) vs GPT-6 Luna (low)

GPT-6 Luna (low) leads on average score with 7.0 vs 7.0. GPT-6 Luna (low) has the lower benchmark cost at $0.020 vs $0.479. GPT-6 Luna (low) is faster at 21.96s vs 98.19s, with pass rates of 63.6% vs 62.1%.

Last updated at: 2026-09-23

Compared models

Rank
#166
Total Output Tokens
220,942
Response Time (avg)
98.19s
Total Cost
$0.479
Rank
#159
Total Output Tokens
22,605
Response Time (avg)
21.96s
Total Cost
$0.020
Recommended model GPT-6 Luna (low)

It has the best score here (7.0), while costing about 24.8x less than Kimi K2.5 (medium).

Detailed comparison

Metric Kimi K2.5 Kimi K2.5 medium Release: 2026-01-27 GPT-6 Luna GPT-6 Luna low Release: 2026-09-23
Score 7.0 7.0
Rank #166 #159
Reliability 10.0 9.6
Consistency 7.0 8.5
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 63.6% 62.1%
Flaky tests 8 4
Total Runs 66 66
Cost per result 4.849 0.176
Total Cost $0.479 $0.020
Input Price $0.450 / 1M $0.100 / 1M
Output Price $2.250 / 1M $0.500 / 1M
Total Input Tokens 118,496 80,159
Output Tokens 53,522 4,623
Reasoning Tokens 167,420 17,982
Response Time (avg) 98.19s 21.96s
Response Time (max) 281.00s 89.37s
Response Time (total) 1571.05s 483.19s
Parameters 1T total (32B active) ~400B total (~17B active)
Availability Weights available Closed

Model generation showcase

Hamster playing table tennis

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

#166 MoonshotAI: Kimi K2.5

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

#159 GPT-6 Luna

low
Cost
$0.002
Time
19.2s
Tokens
2,598 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
GPT-6 Luna 6.0 7.2 55.6% 1 15.39s 7,302 493 6,655

Quick Compare

Switch Comparison Pair