- Peringkat
- #345
- Total token output
- 40,302
- Waktu respons (rata-rata)
- 3.34s
- Total Biaya
- $0.020
Mercury 2.5 (low) vs Mistral Small 4
Skor rata-rata hampir imbang di 5.1 vs 5.1. Mercury 2.5 (low) memiliki biaya benchmark lebih rendah di $0.020 vs $0.047. Mistral Small 4 lebih cepat di 3.12s vs 3.34s, dengan tingkat keberhasilan 37.7% vs 24.6%.
Model yang Dibandingkan
- Peringkat
- #344
- Total token output
- 10,913
- Waktu respons (rata-rata)
- 3.12s
- Total Biaya
- $0.047
Model yang direkomendasikan
Mercury 2.5 (low)
It has the best score here (5.1), while costing about 2.4x less than Mistral Small 4.
Perbandingan terperinci
| Metrik | Mercury 2.5 Mercury 2.5 low | Mistral Small 4 Mistral Small 4 none |
|---|---|---|
| Skor | 5.1 | 5.1 |
| Peringkat | #345 | #344 |
| Keandalan | 9.8 | 10.0 |
| Konsistensi | 8.2 | 9.6 |
| Percobaan | 69/69 | 69/69 |
| Tes benar | ||
| Tingkat lulus per percobaan | 37.7% | 24.6% |
| Tes tidak stabil | 5 | 1 |
| Total Run | 69 | 69 |
| Biaya per hasil | 0.319 | 0.928 |
| Total Biaya | $0.020 | $0.047 |
| Harga input | $0.040 / 1M | $0.150 / 1M |
| Harga output | $0.150 / 1M | $0.600 / 1M |
| Harga baca cache | $0.004 / 1M | $0.015 / 1M |
| Harga tulis cache | T/A | T/A |
| Total token input | 326,083 | 265,602 |
| Token output | 7,224 | 10,913 |
| Token penalaran | 33,078 | 0 |
| Waktu respons (rata-rata) | 3.34s | 3.12s |
| Waktu respons (maks) | 47.06s | 45.46s |
| Waktu respons (total) | 76.80s | 71.87s |
| Parameter | ~100B | 119B total (6B 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.
#345 Mercury 2.5
low- Biaya
- $0.001
- Waktu
- 2.4s
- Token
- 1,236 tok
#344 Mistral Small 4
none- Biaya
- $0.002
- Waktu
- 10.4s
- Token
- 2,370 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 |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 | 5.0 | 10.0 | 0.0% | 0 | 47.06s | 188,063 | 1,141 | 5,442 | |
| Mistral Small 4 | 5.0 | 10.0 | 0.0% | 0 | 45.46s | 160,885 | 1,101 | 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 |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 | 6.9 | 7.9 | 66.7% | 1 | 799ms | 772 | 209 | 2,969 | |
| Mistral Small 4 | 3.4 | 7.9 | 16.7% | 1 | 395ms | 708 | 182 | 0 |
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 | 5.5 | 10.0 | 33.3% | 0 | 972ms | 7,909 | 521 | 2,269 | |
| Mistral Small 4 | 3.7 | 9.7 | 0.0% | 0 | 901ms | 7,636 | 619 | 0 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 | 3.0 | 10.0 | 0.0% | 0 | 5.16s | 107,683 | 3,750 | 11,351 | |
| Mistral Small 4 | 3.0 | 10.0 | 0.0% | 0 | 7.44s | 79,039 | 8,107 | 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 |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 | 6.5 | 10.0 | 50.0% | 0 | 1.06s | 8,322 | 739 | 1,499 | |
| Mistral Small 4 | 10.0 | 10.0 | 100.0% | 0 | 822ms | 7,914 | 261 | 0 |
| Spesifik domain | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 | 3.6 | 7.2 | 22.2% | 1 | 846ms | 851 | 57 | 2,265 | |
| Mistral Small 4 | 5.3 | 10.0 | 33.3% | 0 | 377ms | 807 | 28 | 0 |
| Kecerdasan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 | 4.4 | 9.9 | 0.0% | 0 | 819ms | 525 | 99 | 748 | |
| Mistral Small 4 | 4.0 | 10.0 | 0.0% | 0 | 729ms | 519 | 205 | 0 |
| Kepatuhan instruksi | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 | 2.9 | 6.0 | 16.7% | 1 | 972ms | 518 | 48 | 1,026 | |
| Mistral Small 4 | 6.5 | 10.0 | 50.0% | 0 | 380ms | 729 | 69 | 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 |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 | 5.9 | 4.5 | 66.7% | 2 | 792ms | 768 | 249 | 2,214 | |
| Mistral Small 4 | 3.1 | 9.9 | 0.0% | 0 | 399ms | 735 | 111 | 0 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 | 9.8 | 10.0 | 100.0% | 0 | 2.72s | 10,440 | 388 | 2,537 | |
| Mistral Small 4 | 10.0 | 10.0 | 100.0% | 0 | 1.40s | 6,420 | 213 | 0 |
| Pengetahuan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 | 3.0 | 10.0 | 0.0% | 0 | 782ms | 232 | 23 | 758 | |
| Mistral Small 4 | 3.0 | 10.0 | 0.0% | 0 | 397ms | 210 | 17 | 0 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
Mercury 2.5lowvsKAT Coder AIR V2.5mediumMercury 2.5lowvsMiMo-V2.5-PrononeMercury 2.5lowvsMistral Small 4mediumKAT Coder AIR V2.5mediumvsMistral Small 4noneApodex 1.1 MinidefaultTersedia gratisvsMercury 2.5lowKAT Coder AIR V2.5highvsMistral Small 4noneApodex 1.1 MinidefaultTersedia gratisvsMistral Small 4noneMercury 2.5lowvsLaguna S 2.1mediumTersedia gratisMistral Small 4nonevsNemotron 3.5 LightninghighTersedia gratisMercury 2.5lowvsKAT Coder AIR V2.5highMistral Small 4nonevsLaguna S 2.1mediumTersedia gratisMercury 2.5lowvsNemotron 3.5 LightninghighTersedia gratis