- Peringkat
- #30
- Total token output
- 38,453
- Waktu respons (rata-rata)
- 6.24s
- Total Biaya
- $0.183
Gemini 3.7 Flash (low) vs Gemini 4 Carbon (high)
Gemini 3.7 Flash (low) unggul dalam skor rata-rata dengan 9.4 vs 9.3. Gemini 3.7 Flash (low) memiliki biaya benchmark lebih rendah di $0.183 vs $6.107. Gemini 3.7 Flash (low) lebih cepat di 6.24s vs 120.04s, dengan tingkat keberhasilan 95.7% vs 97.1%.
Model yang Dibandingkan
- Peringkat
- #36
- Total token output
- 513,770
- Waktu respons (rata-rata)
- 120.04s
- Total Biaya
- $6.107
Model yang direkomendasikan
Gemini 3.7 Flash (low)
It has the best score here (9.4), while costing about 33.5x less than Gemini 4 Carbon (high).
Perbandingan terperinci
| Metrik | Gemini 3.7 Flash Gemini 3.7 Flash low | Gemini 4 Carbon Gemini 4 Carbon high |
|---|---|---|
| Skor | 9.4 | 9.3 |
| Peringkat | #30 | #36 |
| Keandalan | 10.0 | 9.0 |
| Konsistensi | 9.3 | 9.3 |
| Percobaan | 69/69 | 69/69 |
| Tes benar | ||
| Tingkat lulus per percobaan | 95.7% | 97.1% |
| Tes tidak stabil | 2 | 2 |
| Total Run | 69 | 69 |
| Biaya per hasil | 0.868 | 29.080 |
| Total Biaya | $0.183 | $6.107 |
| Harga input | $0.750 / 1M | $2.000 / 1M |
| Harga output | $3.750 / 1M | $10.000 / 1M |
| Harga baca cache | $0.075 / 1M | $0.100 / 1M |
| Harga tulis cache | $0.042 / 1M | $0.188 / 1M |
| Total token input | 188,519 | 484,505 |
| Token output | 7,694 | 6,098 |
| Token penalaran | 30,759 | 507,672 |
| Waktu respons (rata-rata) | 6.24s | 120.04s |
| Waktu respons (maks) | 58.75s | 443.11s |
| Waktu respons (total) | 143.56s | 2760.87s |
| Parameter | ~500B total (~20B aktif) | ~1.2T total (~20B 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.
#30 Gemini 3.7 Flash
low- Biaya
- $0.010
- Waktu
- 23.5s
- Token
- 5,210 tok
#36 Gemini 4 Carbon
high
Reached the allocated time limit (600 seconds) without receiving showcase output.
- Biaya
- $0.000
- Waktu
- 600.0s
- Token
- 0 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 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 58.75s | 98,197 | 1,400 | 0 | |
| Gemini 4 Carbon | 10.0 | 10.0 | 100.0% | 0 | 242.71s | 228,686 | 1,076 | 30,888 |
| 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 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 1.54s | 492 | 99 | 1,398 | |
| Gemini 4 Carbon | 10.0 | 10.0 | 100.0% | 0 | 11.36s | 918 | 181 | 6,246 |
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.7 Flash | 7.6 | 7.2 | 77.8% | 1 | 6.20s | 8,118 | 461 | 11,508 | |
| Gemini 4 Carbon | 10.0 | 10.0 | 100.0% | 0 | 119.00s | 8,448 | 495 | 79,534 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 13.00s | 66,250 | 4,873 | 8,108 | |
| Gemini 4 Carbon | 4.7 | 1.6 | 66.7% | 2 | 399.18s | 205,214 | 3,187 | 143,193 |
| 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 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 2.15s | 7,548 | 278 | 1,093 | |
| Gemini 4 Carbon | 10.0 | 10.0 | 100.0% | 0 | 21.49s | 8,025 | 336 | 8,927 |
| Spesifik domain | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.7 Flash | 8.2 | 7.2 | 88.9% | 1 | 3.09s | 642 | 12 | 3,029 | |
| Gemini 4 Carbon | 10.0 | 10.0 | 100.0% | 0 | 337.62s | 963 | 48 | 198,683 |
| Kecerdasan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 2.76s | 486 | 81 | 1,043 | |
| Gemini 4 Carbon | 10.0 | 10.0 | 100.0% | 0 | 22.70s | 591 | 137 | 3,276 |
| Kepatuhan instruksi | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 2.47s | 615 | 72 | 1,778 | |
| Gemini 4 Carbon | 10.0 | 10.0 | 100.0% | 0 | 24.45s | 825 | 96 | 8,586 |
| 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 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 1.92s | 558 | 166 | 1,580 | |
| Gemini 4 Carbon | 10.0 | 10.0 | 100.0% | 0 | 16.38s | 882 | 226 | 5,881 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 4.10s | 5,457 | 241 | 160 | |
| Gemini 4 Carbon | 10.0 | 10.0 | 100.0% | 0 | 97.59s | 29,692 | 292 | 15,637 |
| Pengetahuan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 2.92s | 156 | 11 | 1,062 | |
| Gemini 4 Carbon | 10.0 | 10.0 | 100.0% | 0 | 43.18s | 261 | 24 | 6,821 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
Seed 2.1 TurbolowvsGemini 4 CarbonhighClaude Opus 5highvsGemini 3.7 FlashlowClaude Opus 5mediumvsGemini 3.7 FlashlowGemini 3.7 FlashlowvsGPT-6.1 TerraxhighClaude Opus 5.5highvsGemini 3.7 FlashlowGemini 3.7 FlashlowvsGPT-6.1 TerramaxGemini 4 CarbonhighvsGPT-6.1 TerralowClaude Opus 5.5mediumvsGemini 4 CarbonhighGemini 4 CarbonhighvsMuse WondermediumGemini 4 CarbonhighvsGPT-6.1 TerraxhighGemini 4 CarbonhighvsGPT-5.5mediumClaude Opus 5mediumvsGemini 4 Carbonhigh