- Peringkat
- #277
- Total token output
- 11,832
- Waktu respons (rata-rata)
- 22.65s
- Total Biaya
- $0.786
Ember-1 vs Step 3.5 Flash (medium)
Skor rata-rata hampir imbang di 5.4 vs 5.4. Step 3.5 Flash (medium) memiliki biaya benchmark lebih rendah di $0.105 vs $0.786. Ember-1 lebih cepat di 22.65s vs 190.48s, dengan tingkat keberhasilan 43.5% vs 49.3%.
Model yang Dibandingkan
- Peringkat
- #276
- Total token output
- 607,130
- Waktu respons (rata-rata)
- 190.48s
- Total Biaya
- $0.105
Model yang direkomendasikan
Step 3.5 Flash (medium)
It has the best score here (5.4), while costing about 7.5x less than Ember-1.
Perbandingan terperinci
| Metrik | Ember-1 Ember-1 none | Step 3.5 Flash Step 3.5 Flash medium |
|---|---|---|
| Skor | 5.4 | 5.4 |
| Peringkat | #277 | #276 |
| Keandalan | 8.8 | 10.0 |
| Konsistensi | 8.6 | 8.3 |
| Percobaan | 69/69 | 66/69 |
| Tes benar | ||
| Tingkat lulus per percobaan | 43.5% | 49.3% |
| Tes tidak stabil | 4 | 3 |
| Total Run | 69 | 66 |
| Biaya per hasil | 9.817 | 1.047 |
| Total Biaya | $0.786 | $0.105 |
| Harga input | $3.000 / 1M | $0.100 / 1M |
| Harga output | $15.000 / 1M | $0.300 / 1M |
| Total token input | 202,617 | 139,086 |
| Token output | 11,832 | 193,584 |
| Token penalaran | 0 | 413,546 |
| Waktu respons (rata-rata) | 22.65s | 190.48s |
| Waktu respons (maks) | 93.12s | 1597.85s |
| Waktu respons (total) | 520.91s | 3238.23s |
| Parameter | ~2.8T total (~104B aktif) | 196B total (11B aktif) |
| Ketersediaan | Tertutup | Sumber terbuka |
Showcase generasi model
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#277 Ember-1
none- Biaya
- $0.156
- Waktu
- 224.6s
- Token
- 10,555 tok
#276 Step 3.5 Flash
medium- Biaya
- $0.008
- Waktu
- 277.1s
- Token
- 23,695 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 | 92.87s | 175,191 | 9,168 | 0 | |
| Step 3.5 Flash | 2.8 | 1.6 | 33.3% | 1 | 172.16s | 73,370 | 4,160 | 34,434 |
| 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 | 5.2 | 7.9 | 41.7% | 1 | 22.37s | 796 | 867 | 0 | |
| Step 3.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 40.57s | 694 | 20,391 | 24,176 |
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Ember-1 | 5.5 | 10.0 | 33.3% | 0 | 1.94s | 7,485 | 393 | 0 | |
| Step 3.5 Flash | 2.4 | 5.2 | 0.0% | 0 | 258.38s | 2,211 | 13,207 | 22,429 |
| Gabungan | 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 | 49.01s | 12,162 | 327 | 0 | |
| Step 3.5 Flash | 6.5 | 10.0 | 50.0% | 0 | 813.71s | 44,914 | 18,150 | 111,004 |
| 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 | 6.4 | 5.9 | 66.7% | 1 | 35.25s | 4,017 | 161 | 0 | |
| Step 3.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 15.01s | 7,368 | 600 | 13,886 |
| 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 | 5.3 | 10.0 | 33.3% | 0 | 21.61s | 804 | 68 | 0 | |
| Step 3.5 Flash | 3.5 | 4.4 | 33.3% | 2 | 311.60s | 682 | 126,213 | 175,555 |
| 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 | 5.0 | 10.0 | 0.0% | 0 | 2.28s | 540 | 160 | 0 | |
| Step 3.5 Flash | 5.5 | 10.0 | 0.0% | 0 | 22.39s | 509 | 240 | 3,506 |
| 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 | 6.4 | 5.8 | 66.7% | 1 | 31.00s | 509 | 81 | 0 | |
| Step 3.5 Flash | 8.3 | 10.0 | 50.0% | 0 | 4.78s | 705 | 2,364 | 3,521 |
| 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 | 2.54s | 840 | 569 | 0 | |
| Step 3.5 Flash | 5.3 | 10.0 | 33.3% | 0 | 7.22s | 711 | 5,630 | 10,861 |
| 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 | 26.44s | 0 | 0 | 0 | |
| Step 3.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 11.91s | 7,701 | 275 | 3,802 |
| 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 | 1.05s | 273 | 38 | 0 | |
| Step 3.5 Flash | 3.0 | 10.0 | 0.0% | 0 | 108.45s | 221 | 2,354 | 10,372 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
Step 3.5 FlashmediumvsMiMo-V2.6-FlashnoneStep 3.5 FlashmediumvsHy4 previewlowEmber-1nonevsHy4 previewlowNorth Mini CodemediumTersedia gratisvsEmber-1noneGPT-5.6 LunanonevsStep 3.5 FlashmediumEmber-1nonevsGranite 4.2 8BlowGranite 4.2 8BlowvsStep 3.5 FlashmediumKimi K2.5nonevsStep 3.5 FlashmediumQwen3.8 27BnoneTersedia gratisvsStep 3.5 FlashmediumSeed-2.0-CodenonevsStep 3.5 FlashmediumLaguna XS 2.1noneTersedia gratisvsStep 3.5 FlashmediumQwen3.6 35B A3BnonevsStep 3.5 Flashmedium