- Peringkat
- #152
- Total token output
- 42,741
- Waktu respons (rata-rata)
- 7.54s
- Total Biaya
- $0.323
Gemini 3.8 Flash (low) vs Step 3.7 Flash (low)
Skor rata-rata hampir imbang di 7.2 vs 7.2. Gemini 3.8 Flash (low) memiliki biaya benchmark lebih rendah di $0.323 vs $0.449. Gemini 3.8 Flash (low) lebih cepat di 7.54s vs 20.72s, dengan tingkat keberhasilan 81.2% vs 63.8%.
Model yang Dibandingkan
- Peringkat
- #157
- Total token output
- 339,108
- Waktu respons (rata-rata)
- 20.72s
- Total Biaya
- $0.449
Model yang direkomendasikan
Gemini 3.8 Flash (low)
It has the best score here (7.2), while responding about 2.7x faster than Step 3.7 Flash (low).
Perbandingan terperinci
| Metrik | Gemini 3.8 Flash Gemini 3.8 Flash low | Step 3.7 Flash Step 3.7 Flash low |
|---|---|---|
| Skor | 7.2 | 7.2 |
| Peringkat | #152 | #157 |
| Keandalan | 9.9 | 10.0 |
| Konsistensi | 8.2 | 7.9 |
| Percobaan | 69/69 | 69/69 |
| Tes benar | ||
| Tingkat lulus per percobaan | 81.2% | 63.8% |
| Tes tidak stabil | 5 | 6 |
| Total Run | 69 | 69 |
| Biaya per hasil | 2.014 | 4.078 |
| Total Biaya | $0.323 | $0.449 |
| Harga input | $0.750 / 1M | $0.200 / 1M |
| Harga output | $3.750 / 1M | $1.150 / 1M |
| Harga baca cache | $0.075 / 1M | $0.040 / 1M |
| Harga tulis cache | $0.042 / 1M | T/A |
| Total token input | 215,836 | 292,685 |
| Token output | 9,452 | 339,108 |
| Token penalaran | 33,289 | 0 |
| Waktu respons (rata-rata) | 7.54s | 20.72s |
| Waktu respons (maks) | 67.18s | 124.75s |
| Waktu respons (total) | 173.36s | 476.67s |
| Parameter | ~500B total (~20B aktif) | 198B total (11B aktif) |
| Ketersediaan | Tertutup | Sumber terbuka |
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.
#152 Gemini 3.8 Flash
low- Biaya
- $0.030
- Waktu
- 45.8s
- Token
- 8,023 tok
#157 Step 3.7 Flash
low
SVG tidak valid
- Biaya
- $0.004
- Waktu
- 25.3s
- Token
- 3,072 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 3.8 Flash | 6.1 | 3.1 | 66.7% | 1 | 67.18s | 104,063 | 1,417 | 0 | |
| Step 3.7 Flash | 7.4 | 3.8 | 66.7% | 1 | 83.63s | 188,843 | 18,715 | 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 3.8 Flash | 10.0 | 10.0 | 100.0% | 0 | 1.96s | 492 | 171 | 1,054 | |
| Step 3.7 Flash | 8.7 | 7.9 | 91.7% | 1 | 4.02s | 756 | 10,896 | 0 |
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.8 Flash | 5.4 | 7.2 | 44.4% | 1 | 4.31s | 8,118 | 449 | 5,706 | |
| Step 3.7 Flash | 8.2 | 7.2 | 88.9% | 1 | 9.46s | 7,437 | 18,685 | 0 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.8 Flash | 3.8 | 5.8 | 33.3% | 1 | 19.61s | 87,701 | 6,571 | 14,001 | |
| Step 3.7 Flash | 7.3 | 5.8 | 83.3% | 1 | 66.18s | 77,415 | 93,682 | 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 3.8 Flash | 10.0 | 10.0 | 100.0% | 0 | 2.34s | 7,548 | 279 | 1,000 | |
| Step 3.7 Flash | 7.3 | 5.8 | 83.3% | 1 | 2.29s | 7,398 | 2,667 | 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 3.8 Flash | 5.8 | 4.4 | 66.7% | 2 | 6.50s | 642 | 12 | 7,051 | |
| Step 3.7 Flash | 2.9 | 7.2 | 11.1% | 1 | 22.65s | 837 | 48,299 | 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 3.8 Flash | 10.0 | 10.0 | 100.0% | 0 | 1.89s | 486 | 72 | 316 | |
| Step 3.7 Flash | 3.4 | 9.3 | 0.0% | 0 | 7.00s | 525 | 4,604 | 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 3.8 Flash | 10.0 | 10.0 | 100.0% | 0 | 2.79s | 615 | 72 | 1,873 | |
| Step 3.7 Flash | 9.8 | 10.0 | 100.0% | 0 | 1.58s | 735 | 1,857 | 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 3.8 Flash | 10.0 | 10.0 | 100.0% | 0 | 2.25s | 558 | 165 | 1,458 | |
| Step 3.7 Flash | 5.5 | 9.9 | 33.3% | 0 | 1.84s | 756 | 3,564 | 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 3.8 Flash | 10.0 | 10.0 | 100.0% | 0 | 5.51s | 5,457 | 233 | 224 | |
| Step 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 3.25s | 7,746 | 1,360 | 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 3.8 Flash | 10.0 | 10.0 | 100.0% | 0 | 2.29s | 156 | 11 | 606 | |
| Step 3.7 Flash | 3.0 | 10.0 | 0.0% | 0 | 124.75s | 237 | 134,779 | 0 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
Gemini 3.8 FlashlowvsQwen3.8 27BmediumTersedia gratisStep 3.7 FlashlowvsGLM 5mediumLongCat 2.0mediumvsStep 3.7 FlashlowQwen3.6 27BmediumvsStep 3.7 FlashlowGemini 3.8 FlashlowvsQwen3.5 Plus 2026-02-15mediumGemini 3.8 FlashlowvsQwen3.7 FlashhighQwen3.7 FlashhighvsStep 3.7 FlashlowClaude Opus 5nonevsStep 3.7 FlashlowGemini 3.8 FlashlowvsQwen3.5-27BnoneGemini 3.8 FlashlowvsLongCat 2.0mediumGemini 3.8 FlashlowvsGLM 5mediumQwen3.8 27BmediumTersedia gratisvsStep 3.7 Flashlow