- Peringkat
- #400
- Total token output
- 12,557
- Waktu respons (rata-rata)
- 52.45s
- Total Biaya
- $0.105
Gemini 3 Flash Preview (high) vs Decider V1.1 27B (default)
Decider V1.1 27B (default) unggul dalam skor rata-rata dengan 2.6 vs 1.8. Decider V1.1 27B (default) memiliki biaya benchmark lebih rendah di $0.002 vs $0.105. Decider V1.1 27B (default) lebih cepat di 320ms vs 52.45s, dengan tingkat keberhasilan 4.4% vs 17.4%.
Model yang Dibandingkan
- Peringkat
- #395
- Total token output
- 69
- Waktu respons (rata-rata)
- 320ms
- Total Biaya
- $0.002
Model yang direkomendasikan
Decider V1.1 27B (default)
It has the best score here (2.6), while costing about 71.2x less than Gemini 3 Flash Preview (high).
Perbandingan terperinci
| Metrik | Gemini 3 Flash Preview Gemini 3 Flash Preview high | Decider V1.1 27B Decider V1.1 27B default |
|---|---|---|
| Skor | 1.8 | 2.6 |
| Peringkat | #400 | #395 |
| Keandalan | 10.0 | 10.0 |
| Konsistensi | 0.4 | 5.2 |
| Percobaan | 3/69 | 36/69 |
| Tes benar | ||
| Tingkat lulus per percobaan | 4.4% | 17.4% |
| Tes tidak stabil | 0 | 0 |
| Total Run | 3 | 36 |
| Biaya per hasil | 10.470 | 0.037 |
| Total Biaya | $0.105 | $0.002 |
| Harga input | $0.500 / 1M | $0.020 / 1M |
| Harga output | $3.000 / 1M | $0.000 / 1M |
| Harga baca cache | $0.050 / 1M | T/A |
| Harga tulis cache | $0.084 / 1M | T/A |
| Total token input | 134,050 | 73,557 |
| Token output | 1,029 | 69 |
| Token penalaran | 11,528 | 0 |
| Waktu respons (rata-rata) | 52.45s | 320ms |
| Waktu respons (maks) | 52.45s | 491ms |
| Waktu respons (total) | 52.45s | 3.84s |
| Parameter | ~500B total (~20B aktif) | 27B |
| 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.
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 |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 52.45s | 134,050 | 1,029 | 11,528 | |
| Decider V1.1 27B | 0.0 | 0.0 | 0.0% | 0 | 0ms | 0 | 0 | 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 |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 0.0 | 0.0 | 0.0% | 0 | 0ms | 0 | 0 | 0 | |
| Decider V1.1 27B | 4.0 | 7.5 | 25.0% | 0 | 321ms | 7,161 | 9 | 0 |
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 0.0 | 0.0 | 0.0% | 0 | 0ms | 0 | 0 | 0 | |
| Decider V1.1 27B | 4.9 | 6.7 | 33.3% | 0 | 305ms | 32,733 | 12 | 0 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 0.0 | 0.0 | 0.0% | 0 | 0ms | 0 | 0 | 0 | |
| Decider V1.1 27B | 0.0 | 0.0 | 0.0% | 0 | 0ms | 0 | 0 | 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 |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 0.0 | 0.0 | 0.0% | 0 | 0ms | 0 | 0 | 0 | |
| Decider V1.1 27B | 6.5 | 10.0 | 50.0% | 0 | 286ms | 24,396 | 15 | 0 |
| Spesifik domain | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 0.0 | 0.0 | 0.0% | 0 | 0ms | 0 | 0 | 0 | |
| Decider V1.1 27B | 5.3 | 10.0 | 33.3% | 0 | 313ms | 2,874 | 9 | 0 |
| Kecerdasan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 0.0 | 0.0 | 0.0% | 0 | 0ms | 0 | 0 | 0 | |
| Decider V1.1 27B | 0.0 | 0.0 | 0.0% | 0 | 0ms | 0 | 0 | 0 |
| Kepatuhan instruksi | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 0.0 | 0.0 | 0.0% | 0 | 0ms | 0 | 0 | 0 | |
| Decider V1.1 27B | 1.5 | 5.0 | 0.0% | 0 | 333ms | 5,862 | 21 | 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 |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 0.0 | 0.0 | 0.0% | 0 | 0ms | 0 | 0 | 0 | |
| Decider V1.1 27B | 1.7 | 3.3 | 0.0% | 0 | 422ms | 531 | 3 | 0 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 0.0 | 0.0 | 0.0% | 0 | 0ms | 0 | 0 | 0 | |
| Decider V1.1 27B | 0.0 | 0.0 | 0.0% | 0 | 0ms | 0 | 0 | 0 |
| Pengetahuan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 0.0 | 0.0 | 0.0% | 0 | 0ms | 0 | 0 | 0 | |
| Decider V1.1 27B | 0.0 | 0.0 | 0.0% | 0 | 0ms | 0 | 0 | 0 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
Gemini 3 Flash PreviewhighvsD1defaultCommand A+lowvsDecider V1.1 27BdefaultCommand A+nonevsDecider V1.1 27BdefaultGemini 3 Flash PreviewhighvsKev 4BdefaultGemini 3 Flash PreviewhighvsGPT-6 Luna DecisionsdefaultCommand A+highvsDecider V1.1 27BdefaultGemini 3 Flash PreviewhighvsJev 1.13defaultGemini 3 Flash PreviewhighvsSolar DecidedefaultCommand A+mediumvsDecider V1.1 27BdefaultDecider V1.1 27BdefaultvsGrok 4.20noneGemini 3 Flash PreviewhighvsTev1 4B ExperimentaldefaultLing 3.0 TinymediumvsDecider V1.1 27Bdefault