Navigate
Advertise here

GPT-5 Mini (medium) vs DaisyRose 27B (low)

DaisyRose 27B (low) leads on average score with 8.5 vs 8.4. GPT-5 Mini (medium) has the lower benchmark cost at $0.315 vs $0.501. DaisyRose 27B (low) is faster at 27.86s vs 29.42s, with pass rates of 66.7% vs 79.7%.

Last updated at: 2026-11-22

Compared models

Rank
#133
Total Output Tokens
119,211
Response Time (avg)
29.42s
Total Cost
$0.315
Rank
#129
Total Output Tokens
225,850
Response Time (avg)
27.86s
Total Cost
$0.501
Recommended model GPT-5 Mini (medium)

Its score stays close to the best score here (8.4 vs 8.5), while costing about 1.6x less than DaisyRose 27B (low).

Detailed comparison

Metric GPT-5 Mini GPT-5 Mini medium Release: 2025-08-07 DaisyRose 27B DaisyRose 27B low Release: 2026-11-18
Score 8.4 8.5
Rank #133 #129
Reliability 10.0 10.0
Consistency 8.5 8.6
Attempts 69/69 69/69
Tests Correct
Attempt pass rate 66.7% 79.7%
Flaky tests 4 4
Total Runs 69 69
Cost per result 2.247 3.126
Total Cost $0.315 $0.501
Input Price $0.250 / 1M $0.150 / 1M
Output Price $2.000 / 1M $1.875 / 1M
Cache Read Price $0.025 / 1M $0.038 / 1M
Cache Write Price N/A N/A
Total Input Tokens 214,645 510,451
Output Tokens 15,532 10,679
Reasoning Tokens 103,679 215,171
Response Time (avg) 29.42s 27.86s
Response Time (max) 111.48s 226.85s
Response Time (total) 676.56s 640.81s
Parameters ~400B total (~17B active) 27.8B
Availability Closed Open source

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Model generation showcase

Hamster playing table tennis

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

#133 GPT-5 Mini

medium
Cost
$0.007
Time
42.9s
Tokens
3,432 tok

#129 DaisyRose 27B

low
Cost
$0.007
Time
21.5s
Tokens
3,872 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
GPT-5 Mini 10.0 10.0 100.0% 0 27.63s 7,302 658 17,152
DaisyRose 27B 9.9 10.0 100.0% 0 14.18s 8,127 598 23,197

Switch Comparison Pair