Navigasi
AI BENCHY
AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com

DeepSeek V4 Pro vs GLM 5.2

Skor rata-rata hampir imbang di 6.8 vs 6.7. GLM 5.2 memiliki biaya benchmark lebih rendah di $0.153 vs $0.220. GLM 5.2 lebih cepat di 9.65s vs 11.71s, dengan tingkat keberhasilan 47.0% vs 63.6%.

Benchmark dihasilkan dari suite pengujian AI BENCHY pada: 2026-09-04

Peringkat
#150
Total token output
35,547
Waktu respons (rata-rata)
11.71s
Total Biaya
$0.220
Peringkat
#155
Total token output
14,344
Waktu respons (rata-rata)
9.65s
Total Biaya
$0.153
Model yang direkomendasikan GLM 5.2

It has the strongest score in this comparison (6.7) and the best overall balance of cost and response time across all 2 models.

Perbandingan terperinci

Metrik DeepSeek V4 Pro DeepSeek V4 Pro none Rilis: 2026-04-24 GLM 5.2 GLM 5.2 none Rilis: 2026-06-17
Skor 6.8 6.7
Peringkat #150 #155
Keandalan 10.0 10.0
Konsistensi 8.6 9.2
Percobaan 66/66 66/66
Tes benar
Tingkat lulus per percobaan 47.0% 63.6%
Tes tidak stabil 4 2
Total Run 66 66
Biaya per hasil 1.061 1.312
Total Biaya $0.220 $0.153
Harga input $1.002 / 1M $0.966 / 1M
Harga output $2.004 / 1M $3.036 / 1M
Total token input 148,078 112,458
Token output 35,547 14,344
Token penalaran 0 0
Waktu respons (rata-rata) 11.71s 9.65s
Waktu respons (maks) 119.44s 79.65s
Waktu respons (total) 257.67s 212.38s
Parameter 1.6T total (49B aktif) 744B total (40B aktif)
Ketersediaan Sumber terbuka Sumber terbuka

Showcase generasi model

Hamster playing table tennis

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

#150 DeepSeek V4 Pro

none
Reached the allocated time limit (300 seconds) without receiving showcase output.
Biaya
$0.000
Waktu
300.0s
Token
0 tok

#155 GLM 5.2

none
Biaya
$0.033
Waktu
87.7s
Token
7,455 tok

Model teratas berdasarkan skor

Skor vs Total Biaya

Waktu respons (rata-rata)

Skor vs Waktu respons (rata-rata)

Total token output

Skor vs Total token output

Rincian Kategori

Pemrograman Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token input Token output Token penalaran
DeepSeek V4 Pro 5.6 10.0 33.3% 0 13.38s 7,275 5,500 0
GLM 5.2 3.7 9.5 0.0% 0 7.55s 7,263 1,958 0

Perbandingan Cepat

Ganti Pasangan Perbandingan