- Peringkat
- #113
- Total token output
- 487,519
- Waktu respons (rata-rata)
- 65.67s
- Total Biaya
- $1.047
Qwen3.5-122B-A10B (medium) vs Qwen3.7 Flash (low)
Skor rata-rata hampir imbang di 7.1 vs 7.2. Qwen3.7 Flash (low) memiliki biaya benchmark lebih rendah di $0.043 vs $1.047. Qwen3.7 Flash (low) lebih cepat di 38.05s vs 65.67s, dengan tingkat keberhasilan 71.2% vs 66.7%.
- Peringkat
- #111
- Total token output
- 304,019
- Waktu respons (rata-rata)
- 38.05s
- Total Biaya
- $0.043
Model yang direkomendasikan
Qwen3.7 Flash (low)
It has the best score here (7.2), while costing about 24.7x less than Qwen3.5-122B-A10B (medium).
Perbandingan terperinci
| Metrik | Qwen3.5-122B-A10B Qwen3.5-122B-A10B medium | Qwen3.7 Flash Qwen3.7 Flash low |
|---|---|---|
| Skor | 7.1 | 7.2 |
| Peringkat | #113 | #111 |
| Keandalan | 10.0 | 10.0 |
| Konsistensi | 8.5 | 8.0 |
| Percobaan | 66/66 | 66/66 |
| Tes benar | ||
| Tingkat lulus per percobaan | 71.2% | 66.7% |
| Tes tidak stabil | 4 | 6 |
| Total Run | 66 | 66 |
| Biaya per hasil | 8.446 | 0.385 |
| Total Biaya | $1.047 | $0.043 |
| Harga input | $0.260 / 1M | $0.030 / 1M |
| Harga output | $2.080 / 1M | $0.130 / 1M |
| Total token input | 124,780 | 92,191 |
| Token output | 47,694 | 14,286 |
| Token penalaran | 439,825 | 289,733 |
| Waktu respons (rata-rata) | 65.67s | 38.05s |
| Waktu respons (maks) | 519.30s | 394.54s |
| Waktu respons (total) | 1444.68s | 837.05s |
| Parameter | 122B total (10B aktif) | ~35B total (~3B aktif) |
| Ketersediaan | Sumber terbuka | Tertutup |
Showcase generasi model
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#113 Qwen3.5-122B-A10B
medium- Biaya
- $0.019
- Waktu
- 48.7s
- Token
- 6,034 tok
#111 Qwen3.7 Flash
low
SVG tidak valid
- Biaya
- $0.000
- Waktu
- 600.0s
- Token
- 0 tok
Model teratas berdasarkan skor
Skor vs Total Biaya
Waktu respons (rata-rata)
Skor vs Waktu respons (rata-rata)
Total token output
Skor vs Total token output
Rincian Kategori
| Trik anti-AI | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.5-122B-A10B | 10.0 | 10.0 | 100.0% | 0 | 9.75s | 672 | 269 | 16,835 | |
| Qwen3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 10.29s | 672 | 680 | 14,285 |
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.5-122B-A10B | 6.0 | 7.2 | 55.6% | 1 | 114.48s | 7,630 | 8,057 | 82,578 | |
| Qwen3.7 Flash | 6.7 | 7.8 | 55.6% | 1 | 42.36s | 7,893 | 428 | 56,419 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.5-122B-A10B | 6.4 | 5.8 | 66.7% | 1 | 313.55s | 97,886 | 18,373 | 203,450 | |
| Qwen3.7 Flash | 6.4 | 5.8 | 66.7% | 1 | 217.77s | 64,756 | 11,880 | 131,432 |
| 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 |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.5-122B-A10B | 10.0 | 10.0 | 100.0% | 0 | 23.41s | 7,782 | 270 | 16,558 | |
| Qwen3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 15.44s | 7,782 | 270 | 12,503 |
| Spesifik domain | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.5-122B-A10B | 2.9 | 7.2 | 11.1% | 1 | 74.43s | 780 | 19,154 | 61,573 | |
| Qwen3.7 Flash | 3.6 | 7.2 | 22.2% | 1 | 37.60s | 780 | 60 | 38,897 |
| Kecerdasan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.5-122B-A10B | 3.4 | 2.2 | 33.3% | 1 | 34.11s | 344 | 66 | 7,592 | |
| Qwen3.7 Flash | 4.0 | 9.3 | 0.0% | 0 | 14.37s | 516 | 128 | 5,423 |
| Kepatuhan instruksi | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.5-122B-A10B | 10.0 | 10.0 | 100.0% | 0 | 9.88s | 593 | 77 | 7,372 | |
| Qwen3.7 Flash | 8.5 | 6.8 | 83.3% | 1 | 9.88s | 699 | 99 | 8,147 |
| Pemecahan teka-teki | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.5-122B-A10B | 10.0 | 10.0 | 100.0% | 0 | 17.89s | 696 | 284 | 27,575 | |
| Qwen3.7 Flash | 7.3 | 5.2 | 77.8% | 2 | 9.79s | 696 | 382 | 10,763 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.5-122B-A10B | 10.0 | 10.0 | 100.0% | 0 | 4.60s | 8,193 | 322 | 1,226 | |
| Qwen3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 7.66s | 8,193 | 335 | 2,172 |
| Pengetahuan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.5-122B-A10B | 3.0 | 10.0 | 0.0% | 0 | 52.87s | 204 | 822 | 15,066 | |
| Qwen3.7 Flash | 3.0 | 10.0 | 0.0% | 0 | 18.42s | 204 | 24 | 9,692 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
Muse Glimmer 30BmediumvsQwen3.7 FlashlowMuse Glimmer 30BlowvsQwen3.5-122B-A10BmediumQwen3.5-122B-A10BmediumvsStep 3.7 FlashlowMuse Glimmer 30BhighvsQwen3.7 FlashlowQwen3.5-122B-A10BmediumvsSolar Pro 4highKAT-Coder-Pro V2.5highvsQwen3.7 FlashlowMuse Glimmer 30BhighvsQwen3.5-122B-A10BmediumKimi K2.6mediumvsQwen3.7 FlashlowQwen3.7 FlashlowvsSolar Pro 4highKAT-Coder-Pro V2.5highvsQwen3.5-122B-A10BmediumClaude Opus 4.8nonevsQwen3.7 FlashlowDeepSeek V4 Flash 0731mediumvsQwen3.7 Flashlow