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

Trinity Large Preview vs Google: Gemini 3 Flash Preview

Benchmark dihasilkan dari suite pengujian AI BENCHY pada: 2026-04-16

Metrik Trinity Large Preview Trinity Large Preview none Rilis: 2026-01-27 Tersedia gratis Gemini 3 Flash Preview Gemini 3 Flash Preview medium Rilis: 2025-12-17
Skor 5.3 10.0
Peringkat #76 #1
Konsistensi 9.6 10.0
Tes benar
Tingkat lulus per percobaan 29.6% 100.0%
Tes tidak stabil 1 0
Total Run 52 54
Biaya per hasil 0.000 1.740
Total Biaya $0.000 $0.314
Harga input $0.000 / 1M $0.500 / 1M
Harga output $0.000 / 1M $3.000 / 1M
Token output 1,985 2,072
Token penalaran 0 97,041
Waktu respons (rata-rata) 5.07s 17.60s
Waktu respons (maks) 39.47s 79.71s
Waktu respons (total) 91.23s 193.57s

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
Trinity Large Preview 3.0 10.0 0.0% 0 3.02s 593 0
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 4.13s 305 3,490
Pemrograman Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token output Token penalaran
Trinity Large Preview 6.3 10.0 0.0% 0 39.47s 142 0
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 79.71s 432 48,771
Gabungan Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token output Token penalaran
Trinity Large Preview 3.0 10.0 0.0% 0 8.91s 294 0
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 50.16s 351 12,645
Parsing dan ekstraksi data Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token output Token penalaran
Trinity Large Preview 10.0 10.0 100.0% 0 3.26s 186 0
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 4.72s 279 5,333
Spesifik domain Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token output Token penalaran
Trinity Large Preview 5.3 10.0 33.3% 0 877ms 25 0
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 21.12s 12 14,908
Kecerdasan umum Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token output Token penalaran
Trinity Large Preview 4.4 9.9 0.0% 0 2.86s 124 0
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 4.09s 111 1,285
Kepatuhan instruksi Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token output Token penalaran
Trinity Large Preview 4.1 6.7 16.7% 1 1.09s 63 0
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 6.10s 72 4,558
Pemecahan teka-teki Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token output Token penalaran
Trinity Large Preview 5.4 10.0 33.3% 0 3.30s 291 0
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 4.43s 276 4,921
Pemanggilan alat Skor Konsistensi Tingkat lulus per percobaan Tes tidak stabil Tes benar Waktu respons (rata-rata) Token output Token penalaran
Trinity Large Preview 10.0 10.0 100.0% 0 6.67s 267 0
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 10.55s 234 1,130

Perbandingan Cepat

Ganti Pasangan Perbandingan

Trinity Large PreviewnoneTersedia gratisvsMiniMax M2.7mediumTrinity Large PreviewnoneTersedia gratisvsElephantmediumTrinity Large PreviewnoneTersedia gratisvsMistral Small 4mediumTrinity Large PreviewnoneTersedia gratisvsMiniMax M2.5mediumTersedia gratisTrinity Large PreviewnoneTersedia gratisvsgpt-oss-120bmediumTersedia gratisTrinity Large PreviewnoneTersedia gratisvsQwen3 Coder NextmediumTrinity Large PreviewnoneTersedia gratisvsGLM 4.7 FlashmediumClaude Opus 4.7nonevsGemini 3 Flash PreviewmediumTrinity Large PreviewnoneTersedia gratisvsGPT-5 NanomediumTrinity Large PreviewnoneTersedia gratisvsQwen3.5-9BmediumTrinity Large PreviewnoneTersedia gratisvsMercury 2mediumTrinity Large PreviewnoneTersedia gratisvsGrok 4.1 Fastmedium