- Peringkat
- #247
- Total token output
- 18,040
- Waktu respons (rata-rata)
- 4.67s
- Total Biaya
- $0.508
Gemini 3.5 Flash (minimal) vs Mercury 2.5 (medium)
Skor rata-rata hampir imbang di 6.4 vs 6.4. Mercury 2.5 (medium) memiliki biaya benchmark lebih rendah di $0.034 vs $0.508. Gemini 3.5 Flash (minimal) lebih cepat di 4.67s vs 7.74s, dengan tingkat keberhasilan 58.0% vs 63.8%.
Model yang Dibandingkan
- Peringkat
- #246
- Total token output
- 138,946
- Waktu respons (rata-rata)
- 7.74s
- Total Biaya
- $0.034
Model yang direkomendasikan
Mercury 2.5 (medium)
It has the best score here (6.4), while costing about 15.1x less than Gemini 3.5 Flash (minimal).
Perbandingan terperinci
| Metrik | Gemini 3.5 Flash Gemini 3.5 Flash minimal | Mercury 2.5 Mercury 2.5 medium |
|---|---|---|
| Skor | 6.4 | 6.4 |
| Peringkat | #247 | #246 |
| Keandalan | 10.0 | 9.7 |
| Konsistensi | 9.6 | 8.3 |
| Percobaan | 69/69 | 69/69 |
| Tes benar | ||
| Tingkat lulus per percobaan | 58.0% | 63.8% |
| Tes tidak stabil | 1 | 5 |
| Total Run | 69 | 69 |
| Biaya per hasil | 3.903 | 0.280 |
| Total Biaya | $0.508 | $0.034 |
| Harga input | $1.500 / 1M | $0.040 / 1M |
| Harga output | $9.000 / 1M | $0.150 / 1M |
| Harga baca cache | $0.150 / 1M | $0.004 / 1M |
| Harga tulis cache | $0.084 / 1M | T/A |
| Total token input | 230,004 | 317,982 |
| Token output | 18,040 | 3,918 |
| Token penalaran | 0 | 135,028 |
| Waktu respons (rata-rata) | 4.67s | 7.74s |
| Waktu respons (maks) | 49.23s | 107.89s |
| Waktu respons (total) | 107.45s | 178.07s |
| Parameter | ~500B total (~20B aktif) | ~100B |
| 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.
#247 Gemini 3.5 Flash
minimal- Biaya
- $0.041
- Waktu
- 20.4s
- Token
- 4,608 tok
#246 Mercury 2.5
medium- Biaya
- $0.001
- Waktu
- 3.8s
- Token
- 3,386 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 3.5 Flash | 5.0 | 10.0 | 0.0% | 0 | 49.23s | 129,242 | 1,586 | 0 | |
| Mercury 2.5 | 4.7 | 3.1 | 33.3% | 1 | 107.89s | 226,580 | 780 | 18,037 |
| 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 3.5 Flash | 6.5 | 10.0 | 50.0% | 0 | 892ms | 492 | 405 | 0 | |
| Mercury 2.5 | 10.0 | 10.0 | 100.0% | 0 | 1.28s | 773 | 192 | 7,122 |
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.5 Flash | 5.6 | 9.9 | 33.3% | 0 | 2.75s | 8,122 | 3,456 | 0 | |
| Mercury 2.5 | 5.0 | 5.1 | 44.5% | 2 | 3.70s | 7,807 | 488 | 21,857 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.5 Flash | 3.0 | 10.0 | 0.0% | 0 | 14.41s | 76,686 | 11,581 | 0 | |
| Mercury 2.5 | 6.5 | 10.0 | 50.0% | 0 | 9.23s | 62,336 | 1,073 | 34,370 |
| 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 3.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 1.66s | 7,548 | 279 | 0 | |
| Mercury 2.5 | 10.0 | 10.0 | 100.0% | 0 | 2.57s | 8,385 | 582 | 9,343 |
| Spesifik domain | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.5 Flash | 7.7 | 10.0 | 66.7% | 0 | 879ms | 642 | 12 | 0 | |
| Mercury 2.5 | 3.6 | 7.2 | 22.2% | 1 | 4.39s | 852 | 59 | 19,837 |
| Kecerdasan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 922ms | 486 | 117 | 0 | |
| Mercury 2.5 | 4.4 | 9.9 | 0.0% | 0 | 1.60s | 528 | 98 | 2,364 |
| Kepatuhan instruksi | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.5 Flash | 6.4 | 5.8 | 66.7% | 1 | 893ms | 615 | 76 | 0 | |
| Mercury 2.5 | 6.4 | 6.0 | 66.7% | 1 | 1.07s | 520 | 55 | 2,344 |
| 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 3.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 1.45s | 558 | 282 | 0 | |
| Mercury 2.5 | 10.0 | 10.0 | 100.0% | 0 | 1.93s | 766 | 290 | 7,721 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 2.79s | 5,457 | 234 | 0 | |
| Mercury 2.5 | 10.0 | 10.0 | 100.0% | 0 | 3.35s | 9,203 | 269 | 4,641 |
| Pengetahuan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.5 Flash | 3.0 | 10.0 | 0.0% | 0 | 1.76s | 156 | 12 | 0 | |
| Mercury 2.5 | 3.0 | 10.0 | 0.0% | 0 | 4.30s | 232 | 32 | 7,392 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
Gemini 3.5 FlashminimalvsMiMo-V2.5-PromediumMercury 2.5mediumvsBeam 1.0 501B A23BlowGemini 3.5 FlashminimalvsBeam 1.0 501B A23BlowDots 3 Note PreviewhighTersedia gratisvsGemini 3.5 FlashminimalGemini 3.5 FlashminimalvsKimi K2.5mediumDots 3 Note PreviewhighTersedia gratisvsMercury 2.5mediumDots 3 Note PreviewlowTersedia gratisvsGemini 3.5 FlashminimalDots 3 Note PreviewlowTersedia gratisvsMercury 2.5mediumMercury 2.5mediumvsMinimax M3.1 FlashxhighTersedia gratisGemini 3.5 FlashminimalvsMinimax M3.1 FlashxhighTersedia gratisGemini 3.5 FlashminimalvsLongCat 2.0noneMercury 2.5mediumvsLongCat 2.0none