Navigate
AI BENCHY
Advertise here

Kimi K3 (max) vs GPT-5 Mini (medium)

GPT-5 Mini (medium) leads on average score with 8.1 vs 7.9. GPT-5 Mini (medium) has the lower benchmark cost at $0.241 vs $3.467. GPT-5 Mini (medium) is faster at 27.64s vs 142.84s, with pass rates of 77.3% vs 65.2%.

Last updated at: 2026-09-02

Rank
#61
Total Output Tokens
224,128
Response Time (avg)
142.84s
Total Cost
$3.467
Rank
#52
Total Output Tokens
108,019
Response Time (avg)
27.64s
Total Cost
$0.241
Recommended model GPT-5 Mini (medium)

It has the best score here (8.1), while costing about 14.4x less than Kimi K3 (max).

Detailed comparison

Metric Kimi K3 Kimi K3 max Release: 2026-07-16 GPT-5 Mini GPT-5 Mini medium Release: 2025-08-07
Score 7.9 8.1
Rank #61 #52
Reliability 9.0 10.0
Consistency 9.2 8.4
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 77.3% 65.2%
Flaky tests 2 4
Total Runs 66 66
Cost per result 21.668 2.006
Total Cost $3.467 $0.241
Input Price $3.000 / 1M $0.250 / 1M
Output Price $15.000 / 1M $2.000 / 1M
Total Input Tokens 34,960 98,383
Output Tokens 2,887 14,409
Reasoning Tokens 221,241 93,610
Response Time (avg) 142.84s 27.64s
Response Time (max) 766.58s 111.48s
Response Time (total) 2714.02s 608.02s
Parameters 2.8T total (104B 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.

#61 MoonshotAI: Kimi K3

max
Cost
$0.281
Time
506.9s
Tokens
18,863 tok

#52 GPT-5 Mini

medium
Cost
$0.007
Time
42.9s
Tokens
3,432 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 K3 10.0 10.0 100.0% 0 325.79s 8,061 460 84,012
GPT-5 Mini 10.0 10.0 100.0% 0 27.63s 7,302 658 17,152

Quick Compare

Switch Comparison Pair