- Peringkat
- #163
- Total token output
- 121,223
- Waktu respons (rata-rata)
- 58.14s
- Total Biaya
- $2.405
Ember-1 (high) vs Qwen3.5-Flash (medium)
Ember-1 (high) unggul dalam skor rata-rata dengan 6.9 vs 6.8. Qwen3.5-Flash (medium) memiliki biaya benchmark lebih rendah di $0.184 vs $2.405. Ember-1 (high) lebih cepat di 58.14s vs 83.68s, dengan tingkat keberhasilan 71.0% vs 66.7%.
Model yang Dibandingkan
- Peringkat
- #169
- Total token output
- 531,668
- Waktu respons (rata-rata)
- 83.68s
- Total Biaya
- $0.184
Model yang direkomendasikan
Qwen3.5-Flash (medium)
Its score stays close to the best score here (6.8 vs 6.9), while costing about 13.1x less than Ember-1 (high).
Perbandingan terperinci
| Metrik | Ember-1 Ember-1 high | Qwen3.5-Flash Qwen3.5-Flash medium |
|---|---|---|
| Skor | 6.9 | 6.8 |
| Peringkat | #163 | #169 |
| Keandalan | 8.6 | 10.0 |
| Konsistensi | 7.2 | 7.9 |
| Percobaan | 69/69 | 69/69 |
| Tes benar | ||
| Tingkat lulus per percobaan | 71.0% | 66.7% |
| Tes tidak stabil | 8 | 6 |
| Total Run | 69 | 69 |
| Biaya per hasil | 20.041 | 1.533 |
| Total Biaya | $2.405 | $0.184 |
| Harga input | $3.000 / 1M | $0.065 / 1M |
| Harga output | $15.000 / 1M | $0.260 / 1M |
| Total token input | 195,489 | 349,177 |
| Token output | 12,475 | 54,279 |
| Token penalaran | 108,748 | 477,389 |
| Waktu respons (rata-rata) | 58.14s | 83.68s |
| Waktu respons (maks) | 255.06s | 515.38s |
| Waktu respons (total) | 1337.19s | 1840.92s |
| Parameter | ~2.8T total (~104B aktif) | ~35B total (~3B aktif) |
| Ketersediaan | Tertutup | Tertutup |
Showcase generasi model
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#163 Ember-1
high- Biaya
- $0.038
- Waktu
- 55.1s
- Token
- 2,671 tok
#169 Qwen3.5-Flash
medium- Biaya
- $0.002
- Waktu
- 25.8s
- Token
- 4,294 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
| Tugas agen | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Ember-1 | 6.1 | 3.1 | 66.7% | 1 | 88.31s | 146,912 | 5,130 | 5,968 | |
| Qwen3.5-Flash | 10.0 | 10.0 | 100.0% | 0 | 67.72s | 230,669 | 18,822 | 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 |
|---|---|---|---|---|---|---|---|---|---|
| Ember-1 | 8.7 | 7.9 | 91.7% | 1 | 24.05s | 1,544 | 886 | 992 | |
| Qwen3.5-Flash | 10.0 | 10.0 | 100.0% | 0 | 59.11s | 672 | 383 | 32,992 |
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Ember-1 | 8.2 | 7.2 | 88.9% | 1 | 72.23s | 7,144 | 1,281 | 23,093 | |
| Qwen3.5-Flash | 3.7 | 7.2 | 22.2% | 1 | 58.87s | 6,685 | 302 | 90,081 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Ember-1 | 6.4 | 5.8 | 66.7% | 1 | 79.89s | 28,994 | 1,667 | 6,614 | |
| Qwen3.5-Flash | 6.4 | 5.8 | 66.7% | 1 | 266.58s | 94,507 | 10,679 | 204,282 |
| 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 |
|---|---|---|---|---|---|---|---|---|---|
| Ember-1 | 7.3 | 5.9 | 83.3% | 1 | 36.10s | 6,076 | 230 | 1,228 | |
| Qwen3.5-Flash | 7.3 | 5.9 | 83.3% | 1 | 56.99s | 6,061 | 235 | 16,237 |
| Spesifik domain | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Ember-1 | 2.9 | 4.4 | 22.2% | 2 | 175.49s | 1,154 | 1,023 | 61,582 | |
| Qwen3.5-Flash | 2.9 | 7.2 | 11.1% | 1 | 143.82s | 590 | 23,231 | 30,394 |
| Kecerdasan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Ember-1 | 10.0 | 10.0 | 100.0% | 0 | 4.49s | 744 | 194 | 304 | |
| Qwen3.5-Flash | 6.1 | 3.1 | 66.7% | 1 | 40.05s | 516 | 99 | 38,486 |
| Kepatuhan instruksi | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Ember-1 | 7.1 | 5.8 | 83.3% | 1 | 33.38s | 992 | 162 | 784 | |
| Qwen3.5-Flash | 10.0 | 10.0 | 100.0% | 0 | 63.49s | 699 | 98 | 14,139 |
| Pemecahan teka-teki | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Ember-1 | 10.0 | 10.0 | 100.0% | 0 | 4.84s | 1,452 | 390 | 848 | |
| Qwen3.5-Flash | 8.2 | 7.2 | 88.9% | 1 | 27.61s | 381 | 89 | 12,457 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Ember-1 | 3.0 | 10.0 | 0.0% | 0 | 26.45s | 0 | 0 | 0 | |
| Qwen3.5-Flash | 10.0 | 10.0 | 100.0% | 0 | 10.33s | 8,193 | 309 | 1,284 |
| Pengetahuan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Ember-1 | 3.0 | 10.0 | 0.0% | 0 | 65.34s | 477 | 1,512 | 7,335 | |
| Qwen3.5-Flash | 3.0 | 10.0 | 0.0% | 0 | 48.98s | 204 | 32 | 37,037 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
Qwen3.5-FlashmediumvsInklinglowTersedia gratisEmber-1highvsGemini 3.1 Flash LitemediumEmber-1highvsGemma 4 31BmediumTersedia gratisEmber-1highvsGPT-5.6 LunalowClaude Sonnet 5.5lowvsEmber-1highClaude Opus 4.8nonevsEmber-1highGPT-6 SolnonevsQwen3.5-FlashmediumClaude Opus 4.8nonevsQwen3.5-FlashmediumClaude Sonnet 5.5lowvsQwen3.5-FlashmediumGPT-5.6 LunalowvsQwen3.5-FlashmediumEmber-1highvsKimi K2.6mediumEmber-1highvsInklinglowTersedia gratis