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: 2026-04-24

Metrik GPT-5.5 GPT-5.5 medium Rilis: 2026-04-24 GPT-5.4 GPT-5.4 medium Rilis: 2026-03-05 Gemini 3.1 Pro Preview Gemini 3.1 Pro Preview medium Rilis: 2026-02-19 Claude Opus 4.7 Claude Opus 4.7 medium Rilis: 2026-04-16
Skor 9.0 8.2 9.6 9.2
Peringkat #5 #18 #2 #3
Keandalan T/A T/A T/A T/A
Konsistensi 9.2 8.7 10.0 10.0
Tes benar
Tingkat lulus per percobaan 87.0% 79.6% 94.4% 88.9%
Tes tidak stabil 2 3 0 0
Total Run 54 54 54 54
Biaya per hasil 19.226 6.399 3.400 2.790
Total Biaya $2.884 $0.832 $0.578 $0.447
Harga input $5.000 / 1M $2.500 / 1M $2.000 / 1M $5.000 / 1M
Harga output $30.000 / 1M $15.000 / 1M $12.000 / 1M $25.000 / 1M
Token output 1,920 2,169 1,932 5,375
Token penalaran 89,632 48,732 40,542 1,341
Waktu respons (rata-rata) 32.75s 18.63s 15.96s 3.53s
Waktu respons (maks) 332.10s 100.41s 40.61s 21.45s
Waktu respons (total) 589.59s 335.26s 175.52s 60.03s

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
GPT-5.5 10.0 10.0 100.0% 0 4.66s 250 1,335
GPT-5.4 8.3 10.0 75.0% 0 4.11s 240 1,511
Gemini 3.1 Pro Preview 10.0 10.0 100.0% 0 7.90s 112 3,218
Claude Opus 4.7 8.3 10.0 75.0% 0 1.85s 348 0
Pemrograman Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token output Token penalaran
GPT-5.5 10.0 10.0 100.0% 0 9.09s 318 1,391
GPT-5.4 10.0 10.0 100.0% 0 13.03s 389 2,045
Gemini 3.1 Pro Preview 10.0 10.0 100.0% 0 19.88s 405 4,201
Claude Opus 4.7 10.0 10.0 100.0% 0 6.41s 1,141 257
Gabungan Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token output Token penalaran
GPT-5.5 10.0 10.0 100.0% 0 19.29s 312 2,841
GPT-5.4 10.0 10.0 100.0% 0 20.57s 301 3,543
Gemini 3.1 Pro Preview 9.5 10.0 100.0% 0 40.61s 432 9,281
Claude Opus 4.7 10.0 10.0 100.0% 0 21.45s 2,369 1,084
Parsing dan ekstraksi data Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token output Token penalaran
GPT-5.5 10.0 10.0 100.0% 0 4.18s 234 593
GPT-5.4 10.0 10.0 100.0% 0 5.32s 234 804
Gemini 3.1 Pro Preview 10.0 10.0 100.0% 0 7.72s 279 3,904
Claude Opus 4.7 10.0 10.0 100.0% 0 2.37s 324 0
Spesifik domain Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token output Token penalaran
GPT-5.5 5.3 7.2 44.4% 1 164.14s 67 79,625
GPT-5.4 5.3 7.2 44.4% 1 74.27s 61 34,748
Gemini 3.1 Pro Preview 7.7 10.0 66.7% 0 32.73s 18 12,424
Claude Opus 4.7 7.7 10.0 66.7% 0 1.17s 51 0
Kecerdasan umum Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token output Token penalaran
GPT-5.5 10.0 10.0 100.0% 0 4.16s 138 223
GPT-5.4 4.7 3.1 33.3% 1 4.92s 145 321
Gemini 3.1 Pro Preview 10.0 10.0 100.0% 0 11.77s 108 1,179
Claude Opus 4.7 10.0 10.0 100.0% 0 2.87s 256 0
Kepatuhan instruksi Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token output Token penalaran
GPT-5.5 10.0 10.0 100.0% 0 3.36s 93 538
GPT-5.4 10.0 10.0 100.0% 0 3.11s 93 897
Gemini 3.1 Pro Preview 10.0 10.0 100.0% 0 9.56s 72 2,236
Claude Opus 4.7 10.0 10.0 100.0% 0 1.57s 114 0
Pemecahan teka-teki Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token output Token penalaran
GPT-5.5 8.6 7.9 77.8% 1 6.78s 250 2,254
GPT-5.4 8.2 7.2 88.9% 1 9.13s 442 3,832
Gemini 3.1 Pro Preview 10.0 10.0 100.0% 0 7.15s 232 3,117
Claude Opus 4.7 10.0 10.0 100.0% 0 2.51s 399 0
Pemanggilan alat Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token output Token penalaran
GPT-5.5 10.0 10.0 100.0% 0 10.57s 258 832
GPT-5.4 10.0 10.0 100.0% 0 13.28s 264 1,031
Gemini 3.1 Pro Preview 10.0 10.0 100.0% 0 23.15s 274 982
Claude Opus 4.7 10.0 10.0 100.0% 0 4.17s 373 0

Perbandingan Cepat

Ganti Pasangan Perbandingan

DeepSeek V4 ProhighvsGPT-5.4mediumGPT-5.4mediumvsHY3 PreviewlowTersedia gratisGemini 3 Flash PreviewnonevsGPT-5.4mediumGemini 3.1 Flash Lite PreviewlowvsGPT-5.4mediumGemini 3 Flash PreviewlowvsGPT-5.5mediumClaude Opus 4.7nonevsGPT-5.5mediumGPT-5.4mediumvsHY3 PreviewhighTersedia gratisGemini 3.1 Flash Lite PreviewnonevsGPT-5.4mediumDeepSeek V4 FlashhighvsGPT-5.4mediumClaude Opus 4.7nonevsGemini 3.1 Pro PreviewmediumClaude Opus 4.7mediumvsGemini 3 Flash PreviewlowGPT-5.5mediumvsHY3 PreviewhighTersedia gratis