#66 Seed-2.0-Mini
medium- Biaya
- $0.002
- Waktu
- 161.7s
- Token
- 4,379 tok
AI BENCHY Compare
Ringkasan
Gemini 3.5 Flash (high) unggul dalam skor rata-rata dengan 9.8 vs 7.4. Seed-2.0-Mini (medium) memiliki biaya benchmark lebih rendah di $0.044 vs $1.115. Gemini 3.5 Flash (high) lebih cepat di 8.84s vs 80.22s, dengan tingkat keberhasilan 57.1% vs 96.8%.
Benchmark dihasilkan dari suite pengujian AI BENCHY pada: 2026-07-14
| Metrik | Seed-2.0-Mini Seed-2.0-Mini medium | Gemini 3.5 Flash Gemini 3.5 Flash high |
|---|---|---|
| Skor | 7.4 | 9.8 |
| Peringkat | #66 | #1 |
| Keandalan | 6.7 | 10.0 |
| Konsistensi | 9.3 | 9.6 |
| Tes benar | ||
| Tingkat lulus per percobaan | 57.1% | 96.8% |
| Tes tidak stabil | 2 | 1 |
| Total Run | 63 | 63 |
| Biaya per hasil | 0.397 | 5.575 |
| Total Biaya | $0.044 | $1.115 |
| Harga input | $0.100 / 1M | $1.500 / 1M |
| Harga output | $0.400 / 1M | $9.000 / 1M |
| Total token input | 41,904 | 37,594 |
| Token output | 2,555 | 1,975 |
| Token penalaran | 95,974 | 115,638 |
| Waktu respons (rata-rata) | 80.22s | 8.84s |
| Waktu respons (maks) | 262.83s | 34.82s |
| Waktu respons (total) | 1363.72s | 185.57s |
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 |
|---|---|---|---|---|---|---|---|---|---|
| Seed-2.0-Mini | 5.5 | 9.8 | 33.3% | 0 | 220.48s | 3,823 | 464 | 34,964 | |
| Gemini 3.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 22.96s | 8,118 | 456 | 47,129 |
Ganti Pasangan Perbandingan