- Peringkat
- #104
- Total token output
- 424,019
- Waktu respons (rata-rata)
- 120.40s
- Total Biaya
- $4.016
Qwen3.8 2.4T A95B (low) vs Inkling (high)
Skor rata-rata hampir imbang di 8.4 vs 8.4. Inkling (high) memiliki biaya benchmark lebih rendah di $1.238 vs $4.016. Inkling (high) lebih cepat di 62.72s vs 120.40s, dengan tingkat keberhasilan 73.9% vs 78.3%.
Model yang Dibandingkan
- Peringkat
- #108
- Total token output
- 249,242
- Waktu respons (rata-rata)
- 62.72s
- Total Biaya
- $1.238
Model yang direkomendasikan
Inkling (high)
It has the best score here (8.4), while costing about 3.2x less than Qwen3.8 2.4T A95B (low).
Perbandingan terperinci
| Metrik | Qwen3.8 2.4T A95B Qwen3.8 2.4T A95B low | Inkling Inkling high Tersedia gratis |
|---|---|---|
| Skor | 8.4 | 8.4 |
| Peringkat | #104 | #108 |
| Keandalan | 9.6 | 10.0 |
| Konsistensi | 9.2 | 9.0 |
| Percobaan | 69/69 | 69/69 |
| Tes benar | ||
| Tingkat lulus per percobaan | 73.9% | 78.3% |
| Tes tidak stabil | 2 | 3 |
| Total Run | 69 | 69 |
| Biaya per hasil | 19.825 | 7.812 |
| Total Biaya | $4.016 | $1.238 |
| Harga input | $2.000 / 1M | $0.950 / 1M |
| Harga output | $6.000 / 1M | $4.050 / 1M |
| Harga baca cache | $0.250 / 1M | $0.160 / 1M |
| Harga tulis cache | T/A | T/A |
| Total token input | 313,881 | 240,395 |
| Token output | 123,706 | 7,169 |
| Token penalaran | 388,328 | 242,073 |
| Waktu respons (rata-rata) | 120.40s | 62.72s |
| Waktu respons (maks) | 534.21s | 327.51s |
| Waktu respons (total) | 2769.16s | 1442.48s |
| Parameter | 2.4T total (95B aktif) | 975B total (41B aktif) |
| Ketersediaan | Bobot tersedia | 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.
#104 Qwen3.8 2.4T A95B
low- Biaya
- $0.100
- Waktu
- 193.2s
- Token
- 16,767 tok
#108 Thinking Machines: Inkling
high- Biaya
- $0.005
- Waktu
- 32.2s
- Token
- 1,275 tok
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 |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.8 2.4T A95B | 10.0 | 10.0 | 100.0% | 0 | 151.76s | 200,602 | 2,661 | 13,832 | |
| Inkling | 10.0 | 10.0 | 100.0% | 0 | 66.01s | 153,640 | 1,112 | 11,503 |
| Trik anti-AI | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.8 2.4T A95B | 10.0 | 10.0 | 100.0% | 0 | 22.04s | 1,104 | 397 | 4,814 | |
| Inkling | 10.0 | 10.0 | 100.0% | 0 | 12.68s | 702 | 455 | 7,204 |
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.8 2.4T A95B | 7.8 | 9.3 | 66.7% | 0 | 172.53s | 6,716 | 21,405 | 57,399 | |
| Inkling | 8.5 | 10.0 | 66.7% | 0 | 148.36s | 7,374 | 430 | 78,982 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.8 2.4T A95B | 8.2 | 6.9 | 66.7% | 1 | 231.85s | 85,267 | 8,008 | 50,681 | |
| Inkling | 7.3 | 5.8 | 83.3% | 1 | 63.78s | 61,296 | 3,854 | 19,895 |
| 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 |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.8 2.4T A95B | 10.0 | 10.0 | 100.0% | 0 | 22.27s | 7,956 | 839 | 2,445 | |
| Inkling | 10.0 | 10.0 | 100.0% | 0 | 8.19s | 7,068 | 216 | 2,349 |
| Spesifik domain | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.8 2.4T A95B | 3.2 | 9.3 | 0.0% | 0 | 287.65s | 1,008 | 16,133 | 156,114 | |
| Inkling | 7.7 | 10.0 | 66.7% | 0 | 174.68s | 692 | 61 | 86,556 |
| Kecerdasan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.8 2.4T A95B | 6.1 | 3.1 | 66.7% | 1 | 22.97s | 606 | 44 | 1,497 | |
| Inkling | 10.0 | 10.0 | 100.0% | 0 | 6.53s | 501 | 182 | 1,151 |
| Kepatuhan instruksi | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.8 2.4T A95B | 9.8 | 10.0 | 100.0% | 0 | 19.54s | 903 | 263 | 1,480 | |
| Inkling | 9.8 | 10.0 | 100.0% | 0 | 7.00s | 708 | 93 | 2,098 |
| Pemecahan teka-teki | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.8 2.4T A95B | 10.0 | 10.0 | 100.0% | 0 | 43.37s | 1,026 | 1,154 | 25,563 | |
| Inkling | 6.9 | 4.9 | 77.8% | 2 | 10.69s | 714 | 429 | 4,623 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.8 2.4T A95B | 10.0 | 10.0 | 100.0% | 0 | 25.88s | 8,481 | 302 | 975 | |
| Inkling | 3.0 | 10.0 | 0.0% | 0 | 6.52s | 7,481 | 307 | 601 |
| Pengetahuan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.8 2.4T A95B | 3.0 | 10.0 | 0.0% | 0 | 422.46s | 212 | 72,500 | 73,528 | |
| Inkling | 3.0 | 10.0 | 0.0% | 0 | 153.57s | 219 | 30 | 27,111 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
Nemotron 3.5 Super VLhighTersedia gratisvsQwen3.8 2.4T A95BlowGPT-5 MinimediumvsQwen3.8 2.4T A95BlowMuse Glimmer 30BxhighvsQwen3.8 2.4T A95BlowGemini 3.1 Pro PreviewmediumvsInklinghighTersedia gratisGemini 3.1 Pro PreviewmediumvsQwen3.8 2.4T A95BlowMuse Glimmer 30BxhighvsInklinghighTersedia gratisGPT-5 MinimediumvsInklinghighTersedia gratisParticle-1minimalvsInklinghighTersedia gratisMuse Spark 1.1highvsQwen3.8 2.4T A95BlowClaude Haiku 5.5maxvsQwen3.8 2.4T A95BlowDeepSeek V4 Flash 0731highvsQwen3.8 2.4T A95BlowParticle-1highvsQwen3.8 2.4T A95Blow