#2 Gemini 3 Flash Preview
medium- Biaya
- $0.010
- Waktu
- 17.9s
- Token
- 3,236 tok
AI BENCHY Compare
Ringkasan
Gemini 3 Flash Preview (medium) unggul dalam skor rata-rata dengan 9.6 vs 7.7. Step 3.7 Flash (low) memiliki biaya benchmark lebih rendah di $0.341 vs $0.667. Step 3.7 Flash (low) lebih cepat di 15.74s vs 18.64s, dengan tingkat keberhasilan 98.4% vs 68.3%.
Benchmark dihasilkan dari suite pengujian AI BENCHY pada: 2026-07-14
| Metrik | Gemini 3 Flash Preview Gemini 3 Flash Preview medium | Step 3.7 Flash Step 3.7 Flash low |
|---|---|---|
| Skor | 9.6 | 7.7 |
| Peringkat | #2 | #51 |
| Keandalan | 10.0 | 10.0 |
| Konsistensi | 9.7 | 8.4 |
| Tes benar | ||
| Tingkat lulus per percobaan | 98.4% | 68.3% |
| Tes tidak stabil | 1 | 4 |
| Total Run | 63 | 63 |
| Biaya per hasil | 3.335 | 2.840 |
| Total Biaya | $0.667 | $0.341 |
| Harga input | $0.500 / 1M | $0.200 / 1M |
| Harga output | $3.000 / 1M | $1.150 / 1M |
| Total token input | 37,017 | 40,101 |
| Token output | 2,006 | 289,325 |
| Token penalaran | 214,153 | 0 |
| Waktu respons (rata-rata) | 18.64s | 15.74s |
| Waktu respons (maks) | 117.26s | 124.75s |
| Waktu respons (total) | 391.35s | 330.63s |
Showcase generasi
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 8.6 | 7.6 | 88.9% | 1 | 84.40s | 8,122 | 462 | 161,084 | |
| Step 3.7 Flash | 8.2 | 7.2 | 88.9% | 1 | 9.46s | 7,437 | 18,685 | 0 |
Ganti Pasangan Perbandingan