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

AI BENCHY Compare

Model yang Dibandingkan

Ringkasan

Perbandingan benchmark Qwen3.6 35B A3B vs Qwen3.5-27B vs DeepSeek V4 FlashDeepSeek V4 Flash unggul pada Skor dengan 8.3. Qwen3.6 35B A3B unggul pada Keandalan dengan 10.0. DeepSeek V4 Flash memiliki Total Biaya terendah di $0.027. Qwen3.6 35B A3B paling cepat di 18.08s.

Model yang direkomendasikan: DeepSeek V4 Flash - It has the best score here (8.3), while costing about 13.0x less than model lain dalam perbandingan ini.

Benchmark dihasilkan dari suite pengujian AI BENCHY pada: 2026-06-18

Metrik Qwen3.6 35B A3B Qwen3.6 35B A3B medium Rilis: 2026-04-20 Qwen3.5-27B Qwen3.5-27B medium Rilis: 2026-02-24 DeepSeek V4 Flash DeepSeek V4 Flash high Rilis: 2026-04-24
Skor 6.7 7.9 8.3
Peringkat #75 #29 #23
Keandalan 10.0 10.0 10.0
Konsistensi 9.6 8.5 8.5
Tes benar
Tingkat lulus per percobaan 63.5% 73.0% 74.6%
Tes tidak stabil 1 4 4
Total Run 63 63 63
Biaya per hasil 1.094 4.901 0.299
Total Biaya $0.146 $0.536 $0.027
Harga input $0.140 / 1M $0.195 / 1M $0.090 / 1M
Harga output $1.000 / 1M $1.560 / 1M $0.180 / 1M
Total token input 16,385 42,164 39,745
Token output 19,632 8,534 10,310
Token penalaran 130,219 329,289 123,501
Waktu respons (rata-rata) 18.08s 68.39s 45.85s
Waktu respons (maks) 86.11s 234.36s 218.13s
Waktu respons (total) 343.61s 1436.24s 962.79s

Showcase generasi

Hamster playing table tennis

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

#75 Qwen3.6 35B A3B

medium
SVG tidak valid
Biaya
$0.000
Waktu
300.0s
Token
0 tok

#29 Qwen3.5-27B

medium
Biaya
$0.008
Waktu
62.0s
Token
3,099 tok

#23 DeepSeek V4 Flash

high
Biaya
$0.003
Waktu
93.1s
Token
7,926 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

Trik anti-AI Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token input Token output Token penalaran
Qwen3.6 35B A3B 10.0 10.0 100.0% 0 6.02s 672 1,154 12,385
Qwen3.5-27B 8.7 7.9 91.7% 1 19.75s 672 569 31,505
DeepSeek V4 Flash 8.3 10.0 75.0% 0 28.51s 540 140 7,770
Pemrograman Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token input Token output Token penalaran
Qwen3.6 35B A3B 7.7 10.0 66.7% 0 50.55s 5,051 7,929 37,223
Qwen3.5-27B 6.2 7.1 55.6% 1 160.69s 7,895 6,381 89,388
DeepSeek V4 Flash 7.8 10.0 66.7% 0 50.60s 7,279 395 34,862
Gabungan Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token input Token output Token penalaran
Qwen3.6 35B A3B 3.0 10.0 0.0% 0 0ms 0 0 0
Qwen3.5-27B 10.0 10.0 100.0% 0 163.96s 14,946 483 9,991
DeepSeek V4 Flash 10.0 10.0 100.0% 0 76.57s 14,016 465 7,347
Parsing dan ekstraksi data Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token input Token output Token penalaran
Qwen3.6 35B A3B 10.0 10.0 100.0% 0 12.99s 7,776 2,591 9,968
Qwen3.5-27B 10.0 10.0 100.0% 0 30.26s 7,782 270 16,150
DeepSeek V4 Flash 10.0 10.0 100.0% 0 28.03s 7,290 201 1,179
Spesifik domain Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token input Token output Token penalaran
Qwen3.6 35B A3B 5.3 7.2 44.4% 1 22.50s 771 6,193 39,116
Qwen3.5-27B 5.3 10.0 33.3% 0 79.53s 553 43 52,368
DeepSeek V4 Flash 4.1 4.4 44.5% 2 100.31s 666 27 59,249
Kecerdasan umum Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token input Token output Token penalaran
Qwen3.6 35B A3B 4.4 9.9 0.0% 0 8.66s 516 129 4,569
Qwen3.5-27B 6.1 3.1 66.7% 1 101.41s 524 70 23,147
DeepSeek V4 Flash 6.1 3.1 66.7% 1 25.15s 471 79 632
Kepatuhan instruksi Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token input Token output Token penalaran
Qwen3.6 35B A3B 10.0 10.0 100.0% 0 7.50s 699 219 7,404
Qwen3.5-27B 10.0 10.0 100.0% 0 19.66s 699 97 11,638
DeepSeek V4 Flash 10.0 10.0 100.0% 0 15.36s 627 63 1,622
Pemecahan teka-teki Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token input Token output Token penalaran
Qwen3.6 35B A3B 8.0 10.0 66.7% 0 5.95s 696 655 9,228
Qwen3.5-27B 8.2 7.7 77.8% 1 59.60s 696 242 70,096
DeepSeek V4 Flash 8.2 7.2 88.9% 1 26.11s 594 196 1,767
Pemanggilan alat Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token input Token output Token penalaran
Qwen3.6 35B A3B 3.0 10.0 0.0% 0 0ms 0 0 0
Qwen3.5-27B 10.0 10.0 100.0% 0 7.45s 8,193 348 1,323
DeepSeek V4 Flash 10.0 10.0 100.0% 0 74.73s 8,079 228 542
Pengetahuan umum Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token input Token output Token penalaran
Qwen3.6 35B A3B 3.0 10.0 0.0% 0 32.90s 204 762 10,326
Qwen3.5-27B 3.0 10.0 0.0% 0 85.11s 204 31 23,683
DeepSeek V4 Flash 3.0 10.0 0.0% 0 54.46s 183 8,516 8,531

Perbandingan Cepat

Ganti Pasangan Perbandingan

DeepSeek V4 FlashhighvsGemini 2.5 FlashmediumGemini 3.5 FlashminimalvsQwen3.6 35B A3BmediumDeepSeek V4 FlashhighvsQwen3.7 PlusmediumDeepSeek V4 FlashhighvsGPT-5.2mediumDeepSeek V4 FlashhighvsNemotron 3 Ultra 550b A55bmediumTersedia gratisGemini 3 Flash PreviewnonevsQwen3.6 35B A3BmediumQwen3.5-27BmediumvsStep 3.7 FlashlowDeepSeek V4 FlashhighvsStep 3.7 FlashmediumDeepSeek V4 FlashhighvsGPT-5.2 ChatnoneSeed-2.0-LitemediumvsDeepSeek V4 FlashhighGemini 3.1 Flash Lite PreviewlowvsQwen3.6 35B A3BmediumDeepSeek V4 FlashhighvsGPT-5.4medium