- Peringkat
- #61
- Total token output
- 298,893
- Waktu respons (rata-rata)
- 30.43s
- Total Biaya
- $0.398
Inkling Small (high) vs Grok 4.5 (medium)
Grok 4.5 (medium) unggul dalam skor rata-rata dengan 8.5 vs 8.4. Inkling Small (high) memiliki biaya benchmark lebih rendah di $0.398 vs $2.042. Inkling Small (high) lebih cepat di 30.43s vs 68.59s, dengan tingkat keberhasilan 69.7% vs 83.3%.
Model yang Dibandingkan
- Peringkat
- #54
- Total token output
- 299,460
- Waktu respons (rata-rata)
- 68.59s
- Total Biaya
- $2.042
Model yang direkomendasikan
Inkling Small (high)
Its score stays close to the best score here (8.4 vs 8.5), while costing about 5.1x less than Grok 4.5 (medium).
Perbandingan terperinci
| Metrik | Inkling Small Inkling Small high | Grok 4.5 Grok 4.5 medium |
|---|---|---|
| Skor | 8.4 | 8.5 |
| Peringkat | #61 | #54 |
| Keandalan | 10.0 | 10.0 |
| Konsistensi | 9.2 | 8.9 |
| Percobaan | 66/66 | 66/66 |
| Tes benar | ||
| Tingkat lulus per percobaan | 69.7% | 83.3% |
| Tes tidak stabil | 2 | 3 |
| Total Run | 66 | 66 |
| Biaya per hasil | 2.868 | 12.007 |
| Total Biaya | $0.398 | $2.042 |
| Harga input | $0.450 / 1M | $2.000 / 1M |
| Harga output | $1.200 / 1M | $6.000 / 1M |
| Total token input | 85,669 | 122,155 |
| Token output | 6,092 | 5,514 |
| Token penalaran | 292,801 | 293,946 |
| Waktu respons (rata-rata) | 30.43s | 68.59s |
| Waktu respons (maks) | 122.60s | 436.38s |
| Waktu respons (total) | 669.38s | 1508.91s |
| Parameter | 276B total (12B aktif) | ~1.7T total (~170B aktif) |
| Ketersediaan | Tertutup | Tertutup |
Showcase generasi model
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#61 Thinking Machines: Inkling Small
high- Biaya
- $0.006
- Waktu
- 34.7s
- Token
- 4,735 tok
#54 SpaceXAI: Grok 4.5
medium- Biaya
- $0.044
- Waktu
- 59.4s
- Token
- 7,512 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
| Trik anti-AI | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Inkling Small | 10.0 | 10.0 | 100.0% | 0 | 6.30s | 702 | 335 | 9,678 | |
| Grok 4.5 | 10.0 | 10.0 | 100.0% | 0 | 23.50s | 2,991 | 147 | 4,018 |
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Inkling Small | 10.0 | 10.0 | 100.0% | 0 | 93.23s | 7,374 | 463 | 120,474 | |
| Grok 4.5 | 7.6 | 7.2 | 77.8% | 1 | 155.69s | 9,579 | 390 | 104,634 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Inkling Small | 9.9 | 10.0 | 100.0% | 0 | 40.41s | 61,630 | 4,001 | 28,812 | |
| Grok 4.5 | 10.0 | 10.0 | 100.0% | 0 | 29.01s | 83,730 | 4,154 | 16,180 |
| 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 |
|---|---|---|---|---|---|---|---|---|---|
| Inkling Small | 10.0 | 10.0 | 100.0% | 0 | 3.99s | 7,068 | 216 | 2,763 | |
| Grok 4.5 | 10.0 | 10.0 | 100.0% | 0 | 6.29s | 8,937 | 225 | 3,657 |
| Spesifik domain | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Inkling Small | 5.3 | 10.0 | 33.3% | 0 | 56.28s | 804 | 69 | 84,578 | |
| Grok 4.5 | 5.3 | 7.2 | 44.4% | 1 | 249.34s | 2,221 | 11 | 140,815 |
| Kecerdasan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Inkling Small | 5.3 | 10.0 | 0.0% | 0 | 3.62s | 501 | 153 | 1,395 | |
| Grok 4.5 | 6.5 | 3.4 | 66.7% | 1 | 12.84s | 1,077 | 71 | 2,384 |
| Kepatuhan instruksi | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Inkling Small | 9.8 | 10.0 | 100.0% | 0 | 3.94s | 708 | 94 | 2,742 | |
| Grok 4.5 | 9.8 | 10.0 | 100.0% | 0 | 6.06s | 1,857 | 57 | 2,728 |
| Pemecahan teka-teki | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Inkling Small | 4.8 | 4.4 | 44.5% | 2 | 14.39s | 714 | 482 | 18,286 | |
| Grok 4.5 | 10.0 | 10.0 | 100.0% | 0 | 7.75s | 2,430 | 254 | 3,641 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Inkling Small | 3.0 | 10.0 | 0.0% | 0 | 2.91s | 5,949 | 249 | 577 | |
| Grok 4.5 | 10.0 | 10.0 | 100.0% | 0 | 6.57s | 8,544 | 192 | 968 |
| Pengetahuan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Inkling Small | 3.0 | 10.0 | 0.0% | 0 | 49.27s | 219 | 30 | 23,496 | |
| Grok 4.5 | 3.0 | 10.0 | 0.0% | 0 | 74.44s | 789 | 13 | 14,921 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
DeepSeek V4.1 FlashhighvsGrok 4.5mediumDeepSeek V4.1 FlashlowvsGrok 4.5mediumMuse Spark 1.2lowvsGrok 4.5mediumSeed 2.1 TurbomediumvsInkling SmallhighGPT-5.2mediumvsInkling SmallhighInkling SmallhighvsGrok 4.5lowDeepSeek V4.1 FlashmaxvsInkling SmallhighInkling SmallhighvsGrok 4.6mediumMuse Spark 1.1lowvsInkling SmallhighQwen3.8 27BhighvsGrok 4.5mediumMuse Spark 1.2lowvsInkling SmallhighQwen3.8 MaxlowvsGrok 4.5medium