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

Benchmark dihasilkan dari suite pengujian AI BENCHY pada: 2026-04-27

Metrik DeepSeek V4 Pro DeepSeek V4 Pro high Rilis: 2026-04-24 DeepSeek V4 Flash DeepSeek V4 Flash high Rilis: 2026-04-24 DeepSeek V3.2 DeepSeek V3.2 medium Rilis: 2025-12-01 Kimi K2.6 Kimi K2.6 medium Rilis: 2026-04-20
Skor 6.8 7.8 8.0 7.7
Peringkat #63 #41 #37 #46
Keandalan 8.4 10.0 T/A T/A
Konsistensi 8.0 7.8 8.2 8.3
Tes benar
Tingkat lulus per percobaan 73.2% 79.6% 79.6% 74.1%
Tes tidak stabil 4 5 4 4
Total Run 54 54 52 54
Biaya per hasil 1.825 0.277 0.231 6.563
Total Biaya $0.201 $0.031 $0.028 $0.722
Harga input $0.435 / 1M $0.140 / 1M $0.252 / 1M $0.745 / 1M
Harga output $0.870 / 1M $0.280 / 1M $0.378 / 1M $4.655 / 1M
Token output 11,876 1,765 7,554 80,759
Token penalaran 45,999 90,299 45,588 179,814
Waktu respons (rata-rata) 60.02s 45.41s 43.49s 45.20s
Waktu respons (maks) 358.35s 218.13s 180.92s 215.85s
Waktu respons (total) 1080.31s 817.30s 782.73s 768.37s

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 output Token penalaran
DeepSeek V4 Pro 7.4 10.0 75.0% 0 16.53s 71 3,617
DeepSeek V4 Flash 8.3 10.0 75.0% 0 28.51s 140 7,770
DeepSeek V3.2 8.4 9.9 75.0% 0 30.72s 3,773 7,523
Kimi K2.6 7.0 8.0 66.7% 1 11.59s 7,115 8,934
Pemrograman Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token output Token penalaran
DeepSeek V4 Pro 2.6 0.0 50.0% 1 51.77s 105 2,641
DeepSeek V4 Flash 10.0 10.0 100.0% 0 62.48s 369 9,361
DeepSeek V3.2 4.7 1.6 66.7% 1 180.92s 626 6,792
Kimi K2.6 10.0 10.0 100.0% 0 106.96s 3,236 18,817
Gabungan Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token output Token penalaran
DeepSeek V4 Pro 6.6 10.0 100.0% 0 64.72s 183 1,946
DeepSeek V4 Flash 10.0 10.0 100.0% 0 76.57s 465 7,347
DeepSeek V3.2 10.0 10.0 100.0% 0 93.11s 571 6,296
Kimi K2.6 10.0 10.0 100.0% 0 40.96s 711 13,876
Parsing dan ekstraksi data Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token output Token penalaran
DeepSeek V4 Pro 8.8 10.0 100.0% 0 23.62s 229 1,710
DeepSeek V4 Flash 10.0 10.0 100.0% 0 28.03s 201 1,179
DeepSeek V3.2 10.0 10.0 100.0% 0 36.09s 207 7,693
Kimi K2.6 10.0 10.0 100.0% 0 20.38s 316 11,305
Spesifik domain Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token output Token penalaran
DeepSeek V4 Pro 3.0 6.9 16.7% 1 205.66s 10,529 28,089
DeepSeek V4 Flash 4.1 4.4 44.5% 2 100.31s 27 59,249
DeepSeek V3.2 5.3 7.2 44.4% 1 21.78s 15 4,933
Kimi K2.6 5.3 7.2 44.4% 1 202.38s 47,035 98,262
Kecerdasan umum Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token output Token penalaran
DeepSeek V4 Pro 6.1 3.1 66.7% 1 25.09s 76 1,152
DeepSeek V4 Flash 6.1 3.1 66.7% 1 25.15s 79 632
DeepSeek V3.2 5.4 2.5 66.7% 1 31.30s 68 2,366
Kimi K2.6 10.0 10.0 100.0% 0 17.83s 3,981 4,472
Kepatuhan instruksi Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token output Token penalaran
DeepSeek V4 Pro 10.0 10.0 100.0% 0 41.16s 205 2,416
DeepSeek V4 Flash 10.0 10.0 100.0% 0 15.36s 63 1,622
DeepSeek V3.2 10.0 10.0 100.0% 0 35.78s 1,397 2,845
Kimi K2.6 10.0 10.0 100.0% 0 12.53s 3,977 5,269
Pemecahan teka-teki Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token output Token penalaran
DeepSeek V4 Pro 6.9 7.0 83.3% 1 34.92s 106 3,835
DeepSeek V4 Flash 6.4 4.5 77.8% 2 25.53s 193 2,597
DeepSeek V3.2 8.2 7.2 88.9% 1 36.87s 390 6,281
Kimi K2.6 5.0 5.2 44.5% 2 25.59s 14,140 17,868
Pemanggilan alat Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token output Token penalaran
DeepSeek V4 Pro 10.0 10.0 100.0% 0 21.33s 372 593
DeepSeek V4 Flash 10.0 10.0 100.0% 0 74.73s 228 542
DeepSeek V3.2 10.0 10.0 100.0% 0 34.81s 507 859
Kimi K2.6 10.0 10.0 100.0% 0 8.92s 248 1,011

Perbandingan Cepat

Ganti Pasangan Perbandingan

DeepSeek V4 ProhighvsQwen3.5 Plus 2026-02-15noneDeepSeek V4 FlashhighvsGLM 5V TurbomediumDeepSeek V4 ProhighvsGPT-5.5noneDeepSeek V4 FlashhighvsQwen3.5-FlashmediumDeepSeek V4 FlashhighvsGLM 5.1mediumDeepSeek V4 FlashhighvsStep 3.5 FlashmediumKimi K2.6mediumvsGPT-5.3 ChatnoneDeepSeek V4 ProhighvsNemotron 3 SupermediumTersedia gratisDeepSeek V3.2mediumvsGPT-5.2 ChatnoneDeepSeek V4 FlashhighvsGemini 3.1 Flash Lite PreviewnoneDeepSeek V3.2mediumvsGemini 3.1 Flash Lite PreviewnoneDeepSeek V4 FlashhighvsGPT-5.2 Chatnone