- Peringkat
- #349
- Total token output
- 2,169
- Waktu respons (rata-rata)
- 2.83s
- Total Biaya
- $0.008
Trinity Large Preview (default) vs Granite 4.2 8B
Skor rata-rata hampir imbang di 4.4 vs 4.4. Trinity Large Preview (default) memiliki biaya benchmark lebih rendah di $0.008 vs $0.037. Trinity Large Preview (default) lebih cepat di 2.83s vs 84.66s, dengan tingkat keberhasilan 20.3% vs 15.9%.
Model yang Dibandingkan
- Peringkat
- #350
- Total token output
- 133,268
- Waktu respons (rata-rata)
- 84.66s
- Total Biaya
- $0.037
Model yang direkomendasikan
Trinity Large Preview (default)
It has the best score here (4.4), while costing about 4.7x less than Granite 4.2 8B.
Perbandingan terperinci
| Metrik | Trinity Large Preview Trinity Large Preview default Tersedia gratis | Granite 4.2 8B Granite 4.2 8B none |
|---|---|---|
| Skor | 4.4 | 4.4 |
| Peringkat | #349 | #350 |
| Keandalan | 10.0 | 9.1 |
| Konsistensi | 9.0 | 9.3 |
| Percobaan | 66/69 | 69/69 |
| Tes benar | ||
| Tingkat lulus per percobaan | 20.3% | 15.9% |
| Tes tidak stabil | 2 | 2 |
| Total Run | 66 | 69 |
| Biaya per hasil | 0.017 | 1.206 |
| Total Biaya | $0.008 | $0.037 |
| Harga input | $0.243 / 1M | $0.060 / 1M |
| Harga output | $0.243 / 1M | $0.250 / 1M |
| Harga baca cache | T/A | $0.015 / 1M |
| Harga tulis cache | T/A | T/A |
| Total token input | 29,828 | 226,872 |
| Token output | 2,169 | 133,268 |
| Token penalaran | 0 | 0 |
| Waktu respons (rata-rata) | 2.83s | 84.66s |
| Waktu respons (maks) | 14.34s | 747.17s |
| Waktu respons (total) | 56.65s | 1947.17s |
| Parameter | 398B total (13B aktif) | 8B |
| Ketersediaan | Sumber terbuka | 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.
#349 Trinity Large Preview
default
No endpoints found for arcee-ai/trinity-large-preview:free.
- Biaya
- $0.000
- Waktu
- 0.0s
- Token
- 0 tok
#350 IBM: Granite 4.2 8B
none
Provider returned error
- Biaya
- $0.000
- Waktu
- 0.2s
- 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
| Tugas agen | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Preview | 3.0 | 10.0 | 0.0% | 0 | 88ms | 0 | 0 | 0 | |
| Granite 4.2 8B | 5.0 | 10.0 | 0.0% | 0 | 49.21s | 169,086 | 2,463 | 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 |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Preview | 3.1 | 10.0 | 0.0% | 0 | 2.07s | 651 | 550 | 0 | |
| Granite 4.2 8B | 4.9 | 8.1 | 33.3% | 1 | 17.77s | 669 | 6,026 | 0 |
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Preview | 3.7 | 7.7 | 11.1% | 1 | 14.34s | 738 | 397 | 0 | |
| Granite 4.2 8B | 5.5 | 10.0 | 33.3% | 0 | 105.60s | 8,358 | 47,944 | 0 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Preview | 1.5 | 5.0 | 0.0% | 0 | 8.91s | 12,053 | 294 | 0 | |
| Granite 4.2 8B | 3.0 | 10.0 | 0.0% | 0 | 424.28s | 30,500 | 29,755 | 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 |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Preview | 10.0 | 10.0 | 100.0% | 0 | 3.26s | 6,900 | 186 | 0 | |
| Granite 4.2 8B | 2.9 | 5.8 | 16.7% | 1 | 1.05s | 7,629 | 237 | 0 |
| Spesifik domain | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Preview | 5.3 | 10.0 | 33.3% | 0 | 877ms | 738 | 25 | 0 | |
| Granite 4.2 8B | 3.0 | 10.0 | 0.0% | 0 | 53.62s | 696 | 38,145 | 0 |
| Kecerdasan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Preview | 4.5 | 10.0 | 0.0% | 0 | 873ms | 498 | 104 | 0 | |
| Granite 4.2 8B | 5.0 | 10.0 | 0.0% | 0 | 770ms | 534 | 153 | 0 |
| Kepatuhan instruksi | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Preview | 3.5 | 10.0 | 0.0% | 0 | 822ms | 678 | 63 | 0 | |
| Granite 4.2 8B | 3.0 | 10.0 | 0.0% | 0 | 79.50s | 375 | 1,275 | 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 |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Preview | 3.6 | 7.7 | 11.1% | 1 | 1.97s | 669 | 265 | 0 | |
| Granite 4.2 8B | 3.0 | 10.0 | 0.0% | 0 | 107.60s | 472 | 6,964 | 0 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Preview | 10.0 | 10.0 | 100.0% | 0 | 6.67s | 6,699 | 267 | 0 | |
| Granite 4.2 8B | 10.0 | 10.0 | 100.0% | 0 | 1.39s | 8,331 | 291 | 0 |
| Pengetahuan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Preview | 3.0 | 10.0 | 0.0% | 0 | 777ms | 204 | 18 | 0 | |
| Granite 4.2 8B | 3.0 | 10.0 | 0.0% | 0 | 14.60s | 222 | 15 | 0 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
Granite 4.2 8BnonevsKAT Coder AIR V2.5defaultTrinity Large PreviewdefaultTersedia gratisvsNemotron 3 SupernoneTersedia gratisCobuddymediumTersedia gratisvsGranite 4.2 8BnoneTrinity Large PreviewdefaultTersedia gratisvsCobuddymediumTersedia gratisTrinity Large PreviewdefaultTersedia gratisvsMercury 2noneGranite 4.2 8BnonevsRing 2.6 1tdefaultGranite 4.2 8BnonevsLing 2.6 FlashdefaultGranite 4.2 8BnonevsMiniMax M2.5mediumTrinity Large PreviewdefaultTersedia gratisvsMiniMax M2.5mediumTrinity Large PreviewdefaultTersedia gratisvsNemotron 3.5 LightninglowTersedia gratisTrinity Large PreviewdefaultTersedia gratisvsLaguna S 2.1lowTersedia gratisGranite 4.2 8BnonevsNemotron 3.5 LightninglowTersedia gratis