- Peringkat
- #74
- Total token output
- 61,650
- Waktu respons (rata-rata)
- 7.51s
- Total Biaya
- $0.061
Claude Haiku 5.5 (low) vs Gemini 3.8 Flash (medium)
Claude Haiku 5.5 (low) unggul dalam skor rata-rata dengan 8.6 vs 8.0. Claude Haiku 5.5 (low) memiliki biaya benchmark lebih rendah di $0.061 vs $0.769. Claude Haiku 5.5 (low) lebih cepat di 7.51s vs 16.64s, dengan tingkat keberhasilan 76.8% vs 89.9%.
Model yang Dibandingkan
- Peringkat
- #111
- Total token output
- 167,486
- Waktu respons (rata-rata)
- 16.64s
- Total Biaya
- $0.769
Model yang direkomendasikan
Claude Haiku 5.5 (low)
It has the best score here (8.6), while costing about 12.7x less than Gemini 3.8 Flash (medium).
Perbandingan terperinci
| Metrik | Claude Haiku 5.5 Claude Haiku 5.5 low | Gemini 3.8 Flash Gemini 3.8 Flash medium |
|---|---|---|
| Skor | 8.6 | 8.0 |
| Peringkat | #74 | #111 |
| Keandalan | 10.0 | 9.9 |
| Konsistensi | 8.9 | 9.0 |
| Percobaan | 69/69 | 69/69 |
| Tes benar | ||
| Tingkat lulus per percobaan | 76.8% | 89.9% |
| Tes tidak stabil | 3 | 3 |
| Total Run | 69 | 69 |
| Biaya per hasil | 0.378 | 4.046 |
| Total Biaya | $0.061 | $0.769 |
| Harga input | $0.100 / 1M | $0.750 / 1M |
| Harga output | $0.500 / 1M | $3.750 / 1M |
| Harga baca cache | $0.010 / 1M | $0.075 / 1M |
| Harga tulis cache | $0.125 / 1M | $0.042 / 1M |
| Total token input | 296,301 | 187,331 |
| Token output | 10,672 | 7,555 |
| Token penalaran | 50,978 | 159,931 |
| Waktu respons (rata-rata) | 7.51s | 16.64s |
| Waktu respons (maks) | 44.43s | 108.60s |
| Waktu respons (total) | 172.74s | 382.64s |
| Parameter | ~50B | ~500B total (~20B aktif) |
| Ketersediaan | Tertutup | Tertutup |
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.
#74 Claude Haiku 5.5
low- Biaya
- $0.001
- Waktu
- 7.4s
- Token
- 1,851 tok
#111 Gemini 3.8 Flash
medium- Biaya
- $0.037
- Waktu
- 54.6s
- Token
- 9,712 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 |
|---|---|---|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | 10.0 | 10.0 | 100.0% | 0 | 44.43s | 153,966 | 2,991 | 3,811 | |
| Gemini 3.8 Flash | 2.8 | 1.6 | 33.3% | 1 | 63.72s | 91,538 | 489 | 12,089 |
| Trik anti-AI | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | 8.7 | 7.9 | 91.7% | 1 | 2.16s | 858 | 483 | 1,480 | |
| Gemini 3.8 Flash | 10.0 | 10.0 | 100.0% | 0 | 2.66s | 492 | 145 | 3,131 |
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | 7.9 | 7.5 | 77.8% | 1 | 7.30s | 10,608 | 531 | 11,618 | |
| Gemini 3.8 Flash | 8.0 | 9.9 | 66.7% | 0 | 11.69s | 8,118 | 454 | 19,433 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | 10.0 | 10.0 | 100.0% | 0 | 23.94s | 104,796 | 4,741 | 19,543 | |
| Gemini 3.8 Flash | 8.7 | 6.9 | 83.3% | 1 | 60.28s | 71,646 | 5,615 | 59,676 |
| 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 |
|---|---|---|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | 10.0 | 10.0 | 100.0% | 0 | 3.45s | 10,515 | 312 | 1,609 | |
| Gemini 3.8 Flash | 10.0 | 10.0 | 100.0% | 0 | 5.74s | 7,548 | 279 | 4,386 |
| Spesifik domain | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | 5.9 | 7.2 | 55.6% | 1 | 7.35s | 990 | 64 | 9,207 | |
| Gemini 3.8 Flash | 8.2 | 7.2 | 88.9% | 1 | 31.77s | 644 | 12 | 44,973 |
| Kecerdasan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | 4.6 | 9.8 | 0.0% | 0 | 1.38s | 714 | 319 | 0 | |
| Gemini 3.8 Flash | 10.0 | 10.0 | 100.0% | 0 | 3.65s | 486 | 78 | 1,185 |
| Kepatuhan instruksi | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | 9.8 | 10.0 | 100.0% | 0 | 2.20s | 921 | 94 | 515 | |
| Gemini 3.8 Flash | 10.0 | 10.0 | 100.0% | 0 | 4.81s | 615 | 72 | 2,944 |
| Pemecahan teka-teki | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | 7.7 | 10.0 | 66.7% | 0 | 2.76s | 912 | 611 | 1,783 | |
| Gemini 3.8 Flash | 10.0 | 10.0 | 100.0% | 0 | 2.73s | 558 | 151 | 2,720 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | 10.0 | 10.0 | 100.0% | 0 | 4.19s | 11,757 | 354 | 459 | |
| Gemini 3.8 Flash | 10.0 | 10.0 | 100.0% | 0 | 18.47s | 5,530 | 249 | 6,512 |
| Pengetahuan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | 3.0 | 10.0 | 0.0% | 0 | 2.70s | 264 | 172 | 953 | |
| Gemini 3.8 Flash | 10.0 | 10.0 | 100.0% | 0 | 5.94s | 156 | 11 | 2,882 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
Gemini 3.8 FlashmediumvsQwen3.8 Flash NextlowGemini 3.8 FlashmediumvsGPT-5.6 TerralowGemini 3.8 FlashmediumvsGPT-5.6 LunahighClaude Haiku 5.5lowvsGrok 4.6highGemini 3.8 FlashmediumvsGLM 5.3 FlashXmaxClaude Fable 5.1highvsGemini 3.8 FlashmediumClaude Haiku 5.5lowvsDeepSeek V4.1 FlashmaxClaude Haiku 5.5lowvsQwen3.7 MaxmediumGemini 3.8 FlashmediumvsQwen3.7 MaxnoneDeepSeek V4.1 FlashlowvsGemini 3.8 FlashmediumClaude Haiku 5.5lowvsSeed 2.1 TurbomediumClaude Haiku 5.5lowvsMiMo-V2.6-Promedium