- Peringkat
- #172
- Total token output
- 42,400
- Waktu respons (rata-rata)
- 8.51s
- Total Biaya
- $0.254
Gemini 3 Flash Preview (low) vs Step 5 Preview (high)
Skor rata-rata hampir imbang di 6.9 vs 7.0. Gemini 3 Flash Preview (low) memiliki biaya benchmark lebih rendah di $0.254 vs $4.513. Gemini 3 Flash Preview (low) lebih cepat di 8.51s vs 154.41s, dengan tingkat keberhasilan 72.5% vs 52.2%.
Model yang Dibandingkan
- Peringkat
- #169
- Total token output
- 1,581,325
- Waktu respons (rata-rata)
- 154.41s
- Total Biaya
- $4.513
Model yang direkomendasikan
Gemini 3 Flash Preview (low)
It has the best score here (6.9), while costing about 17.8x less than Step 5 Preview (high).
Perbandingan terperinci
| Metrik | Gemini 3 Flash Preview Gemini 3 Flash Preview low | Step 5 Preview Step 5 Preview high |
|---|---|---|
| Skor | 6.9 | 7.0 |
| Peringkat | #172 | #169 |
| Keandalan | 10.0 | 9.5 |
| Konsistensi | 9.3 | 8.5 |
| Percobaan | 69/69 | 69/69 |
| Tes benar | ||
| Tingkat lulus per percobaan | 72.5% | 52.2% |
| Tes tidak stabil | 2 | 4 |
| Total Run | 69 | 69 |
| Biaya per hasil | 1.582 | 45.130 |
| Total Biaya | $0.254 | $4.513 |
| Harga input | $0.500 / 1M | $1.000 / 1M |
| Harga output | $3.000 / 1M | $2.700 / 1M |
| Harga baca cache | $0.050 / 1M | $0.050 / 1M |
| Harga tulis cache | $0.084 / 1M | T/A |
| Total token input | 251,677 | 243,381 |
| Token output | 11,196 | 1,581,325 |
| Token penalaran | 31,204 | 0 |
| Waktu respons (rata-rata) | 8.51s | 154.41s |
| Waktu respons (maks) | 52.64s | 455.72s |
| Waktu respons (total) | 195.76s | 3551.40s |
| Parameter | ~500B total (~20B aktif) | 600B total (27B aktif) |
| Ketersediaan | Tertutup | Tertutup |
Harga cache berlaku untuk token input. Pembacaan memakai kembali prompt tersimpan; penulisan menyimpannya dan dapat menambah biaya. Token output menggunakan harga output.
Showcase generasi model
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#172 Gemini 3 Flash Preview
low- Biaya
- $0.007
- Waktu
- 12.1s
- Token
- 2,289 tok
#169 Step 5 Preview
high- Biaya
- $0.057
- Waktu
- 150.1s
- Token
- 20,970 tok
Rincian Kategori
| Tugas agen | 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 | 5.0 | 10.0 | 0.0% | 0 | 52.64s | 127,990 | 1,624 | 0 | |
| Step 5 Preview | 10.0 | 10.0 | 100.0% | 0 | 55.73s | 150,653 | 10,088 | 0 |
| Trik anti-AI | 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 | 10.0 | 10.0 | 100.0% | 0 | 3.48s | 500 | 281 | 3,082 | |
| Step 5 Preview | 6.5 | 8.0 | 58.3% | 1 | 14.70s | 684 | 11,701 | 0 |
| 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 | 5.8 | 7.2 | 44.4% | 1 | 6.00s | 8,122 | 456 | 7,421 | |
| Step 5 Preview | 2.9 | 10.0 | 0.0% | 0 | 421.68s | 7,383 | 576,000 | 0 |
| Gabungan | 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 | 3.0 | 10.0 | 0.0% | 0 | 10.20s | 99,775 | 7,822 | 0 | |
| Step 5 Preview | 10.0 | 10.0 | 100.0% | 0 | 115.30s | 66,481 | 98,423 | 0 |
| Parsing dan ekstraksi data | 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 | 10.0 | 10.0 | 100.0% | 0 | 9.40s | 7,261 | 279 | 3,656 | |
| Step 5 Preview | 10.0 | 10.0 | 100.0% | 0 | 6.55s | 7,362 | 4,589 | 0 |
| Spesifik domain | 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 | 5.3 | 7.2 | 44.4% | 1 | 9.74s | 648 | 12 | 9,096 | |
| Step 5 Preview | 3.0 | 10.0 | 0.0% | 0 | 333.41s | 783 | 479,743 | 0 |
| Kecerdasan umum | 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 | 10.0 | 10.0 | 100.0% | 0 | 3.68s | 492 | 120 | 981 | |
| Step 5 Preview | 3.4 | 9.3 | 0.0% | 0 | 36.56s | 507 | 5,684 | 0 |
| Kepatuhan instruksi | 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 | 9.9 | 10.0 | 100.0% | 0 | 7.02s | 621 | 71 | 2,752 | |
| Step 5 Preview | 7.3 | 5.8 | 83.3% | 1 | 20.53s | 699 | 5,503 | 0 |
| Pemecahan teka-teki | 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 | 10.0 | 10.0 | 100.0% | 0 | 5.77s | 562 | 288 | 3,168 | |
| Step 5 Preview | 5.8 | 4.4 | 66.7% | 2 | 143.16s | 702 | 196,941 | 0 |
| Pemanggilan alat | 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 | 10.0 | 10.0 | 100.0% | 0 | 4.99s | 5,550 | 234 | 415 | |
| Step 5 Preview | 10.0 | 10.0 | 100.0% | 0 | 4.34s | 7,908 | 653 | 0 |
| Pengetahuan umum | 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 | 10.0 | 10.0 | 100.0% | 0 | 2.75s | 156 | 9 | 633 | |
| Step 5 Preview | 3.0 | 10.0 | 0.0% | 0 | 416.44s | 219 | 192,000 | 0 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
Gemini 3 Flash PreviewlowvsQwen3.5-122B-A10BmediumQwen3.5-122B-A10BmediumvsStep 5 PreviewhighEmber-1lowvsStep 5 PreviewhighStep 5 PreviewhighvsGrok 4.6lowMuse Glimmer 30BlowvsStep 5 PreviewhighKimi K2.7 CodemediumvsStep 5 PreviewhighGemini 3.1 Flash Lite PreviewmediumvsStep 5 PreviewhighGemini 3 Flash PreviewlowvsKimi K2.7 CodemediumGPT-5.2 ChatdefaultvsStep 5 PreviewhighEmber-1highvsGemini 3 Flash PreviewlowGemini 3 Flash PreviewlowvsGPT-5.2 ChatdefaultGemini 3.1 Flash LitemediumvsStep 5 Previewhigh