Navigasi
AI BENCHY
Advertise here

AI BENCHY Compare

Model yang Dibandingkan

Benchmark dihasilkan dari suite pengujian AI BENCHY pada: 2026-05-26

Metrik DeepSeek V4 Pro DeepSeek V4 Pro high Rilis: 2026-04-24 DeepSeek V4 Flash DeepSeek V4 Flash high Rilis: 2026-04-24 Tersedia gratis Ling-2.6-flash Ling-2.6-flash none Rilis: 2026-04-21 GLM 5 GLM 5 medium Rilis: 2026-02-12
Skor 6.6 7.6 5.3 8.2
Peringkat #83 #44 #130 #18
Keandalan 9.3 10.0 10.0 10.0
Konsistensi 8.7 8.4 9.2 8.4
Tes benar
Tingkat lulus per percobaan 63.3% 73.3% 35.1% 81.7%
Tes tidak stabil 3 4 2 4
Total Run 98 98 98 98
Biaya per hasil 2.261 0.329 0.005 1.818
Total Biaya $0.249 $0.040 $0.001 $0.255
Harga input $0.435 / 1M $0.112 / 1M $0.010 / 1M $0.600 / 1M
Harga output $0.870 / 1M $0.224 / 1M $0.030 / 1M $1.920 / 1M
Token output 13,536 11,480 2,992 21,596
Token penalaran 61,786 122,086 0 105,424
Waktu respons (rata-rata) 58.92s 46.36s 9.34s 32.67s
Waktu respons (maks) 358.35s 218.13s 35.34s 99.85s
Waktu respons (total) 1119.51s 927.27s 177.48s 392.01s

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
Ling-2.6-flash 6.8 8.1 58.3% 1 11.81s 573 0
GLM 5 10.0 10.0 100.0% 0 23.66s 480 7,056
Pemrograman Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token output Token penalaran
DeepSeek V4 Pro 2.8 5.0 25.0% 1 51.77s 105 2,641
DeepSeek V4 Flash 6.8 10.0 50.0% 0 58.13s 387 27,101
Ling-2.6-flash 10.0 10.0 100.0% 0 11.21s 381 0
GLM 5 10.0 10.0 100.0% 0 89.47s 2,985 45,706
Gabungan 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 65.02s 465 5,914
DeepSeek V4 Flash 10.0 10.0 100.0% 0 76.57s 465 7,347
Ling-2.6-flash 3.0 10.0 0.0% 0 35.34s 1,069 0
GLM 5 10.0 10.0 100.0% 0 28.96s 662 3,242
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
Ling-2.6-flash 6.5 10.0 50.0% 0 8.48s 246 0
GLM 5 7.1 5.6 83.3% 1 8.90s 567 3,734
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
Ling-2.6-flash 3.0 10.0 0.0% 0 4.95s 24 0
GLM 5 3.5 4.4 33.3% 2 0ms 13,176 14,137
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
Ling-2.6-flash 4.0 10.0 0.0% 0 1.45s 109 0
GLM 5 6.1 3.1 66.7% 1 14.69s 2,020 2,248
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
Ling-2.6-flash 9.8 10.0 100.0% 0 5.52s 81 0
GLM 5 10.0 10.0 100.0% 0 7.25s 1,001 2,129
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 10.0 66.7% 0 34.84s 1,431 11,847
DeepSeek V4 Flash 8.2 7.2 88.9% 1 26.11s 1,374 8,113
Ling-2.6-flash 2.9 7.2 11.1% 1 6.51s 265 0
GLM 5 10.0 10.0 100.0% 0 11.33s 71 13,728
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
Ling-2.6-flash 3.0 10.0 0.0% 0 18.80s 229 0
GLM 5 10.0 10.0 100.0% 0 15.93s 233 994
Pengetahuan umum Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token output Token penalaran
DeepSeek V4 Pro 3.0 10.0 0.0% 0 39.14s 53 3,807
DeepSeek V4 Flash 3.0 10.0 0.0% 0 54.46s 8,516 8,531
Ling-2.6-flash 3.0 10.0 0.0% 0 1.06s 15 0
GLM 5 3.0 10.0 0.0% 0 67.37s 401 12,450

Perbandingan Cepat

Ganti Pasangan Perbandingan

DeepSeek V4 FlashhighTersedia gratisvsMiMo-V2.5-PromediumDeepSeek V4 FlashhighTersedia gratisvsGemini 3.1 Flash Lite PreviewlowDeepSeek V4 ProhighvsGemini 3.1 Flash LitenoneDeepSeek V4 FlashhighTersedia gratisvsQwen3.5-FlashmediumDeepSeek V4 FlashhighTersedia gratisvsQwen3.6 FlashmediumDeepSeek V4 ProhighvsGPT-5.5noneDeepSeek V4 FlashhighTersedia gratisvsQwen3.5 Plus 2026-04-20mediumDeepSeek V4 FlashhighTersedia gratisvsGrok Build 0.1mediumDeepSeek V4 FlashhighTersedia gratisvsGemini 3 Flash PreviewnoneDeepSeek V4 ProhighvsQwen3.6 27BmediumDeepSeek V4 FlashhighTersedia gratisvsMiMo-V2-PromediumDeepSeek V4 ProhighvsGrok Build 0.1none