- Peringkat
- #70
- Total token output
- 919,699
- Waktu respons (rata-rata)
- 61.71s
- Total Biaya
- $0.509
Claude Haiku 5.5 (max) vs Gemini 3.1 Pro Preview (medium)
Claude Haiku 5.5 (max) unggul dalam skor rata-rata dengan 8.5 vs 8.4. Claude Haiku 5.5 (max) memiliki biaya benchmark lebih rendah di $0.509 vs $1.585. Gemini 3.1 Pro Preview (medium) lebih cepat di 22.71s vs 61.71s, dengan tingkat keberhasilan 85.5% vs 89.9%.
Model yang Dibandingkan
- Peringkat
- #74
- Total token output
- 102,691
- Waktu respons (rata-rata)
- 22.71s
- Total Biaya
- $1.585
Model yang direkomendasikan
Claude Haiku 5.5 (max)
It has the best score here (8.5), while costing about 3.1x less than Gemini 3.1 Pro Preview (medium).
Perbandingan terperinci
| Metrik | Claude Haiku 5.5 Claude Haiku 5.5 max | Gemini 3.1 Pro Preview Gemini 3.1 Pro Preview medium |
|---|---|---|
| Skor | 8.5 | 8.4 |
| Peringkat | #70 | #74 |
| Keandalan | 10.0 | 9.8 |
| Konsistensi | 9.6 | 9.6 |
| Percobaan | 69/69 | 69/69 |
| Tes benar | ||
| Tingkat lulus per percobaan | 85.5% | 89.9% |
| Tes tidak stabil | 1 | 1 |
| Total Run | 69 | 69 |
| Biaya per hasil | 2.677 | 7.924 |
| Total Biaya | $0.509 | $1.585 |
| Harga input | $0.100 / 1M | $2.000 / 1M |
| Harga output | $0.500 / 1M | $12.000 / 1M |
| Harga baca cache | $0.010 / 1M | $0.200 / 1M |
| Harga tulis cache | $0.125 / 1M | $0.375 / 1M |
| Total token input | 487,516 | 176,208 |
| Token output | 10,212 | 6,093 |
| Token penalaran | 909,487 | 96,598 |
| Waktu respons (rata-rata) | 61.71s | 22.71s |
| Waktu respons (maks) | 288.94s | 88.68s |
| Waktu respons (total) | 1419.40s | 386.11s |
| Parameter | ~50B | ~1.2T 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.
#70 Claude Haiku 5.5
max
OpenRouter returned no showcase content (finish_reason: error).
- Biaya
- $0.000
- Waktu
- 164.5s
- Token
- 0 tok
#74 Gemini 3.1 Pro Preview
medium- Biaya
- $0.115
- Waktu
- 87.2s
- Token
- 9,629 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 | 4.7 | 1.6 | 66.7% | 1 | 93.30s | 349,997 | 2,345 | 42,315 | |
| Gemini 3.1 Pro Preview | 4.7 | 1.6 | 66.7% | 1 | 56.17s | 83,912 | 861 | 4,592 |
| 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 | 10.0 | 10.0 | 100.0% | 0 | 5.52s | 858 | 401 | 10,159 | |
| Gemini 3.1 Pro Preview | 10.0 | 10.0 | 100.0% | 0 | 7.90s | 498 | 112 | 3,218 |
| 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 | 10.0 | 10.0 | 100.0% | 0 | 55.87s | 10,608 | 532 | 125,988 | |
| Gemini 3.1 Pro Preview | 7.9 | 9.9 | 66.7% | 0 | 40.17s | 8,124 | 435 | 41,247 |
| 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 | 148.38s | 99,980 | 4,909 | 215,518 | |
| Gemini 3.1 Pro Preview | 9.8 | 10.0 | 100.0% | 0 | 40.39s | 67,910 | 3,687 | 23,111 |
| 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 | 11.11s | 10,515 | 311 | 13,476 | |
| Gemini 3.1 Pro Preview | 10.0 | 10.0 | 100.0% | 0 | 7.72s | 7,265 | 279 | 3,904 |
| 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 | 5.3 | 10.0 | 33.3% | 0 | 228.16s | 990 | 18 | 426,269 | |
| Gemini 3.1 Pro Preview | 7.7 | 10.0 | 66.7% | 0 | 20.29s | 644 | 18 | 11,704 |
| 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 | 10.0 | 10.0 | 100.0% | 0 | 42.22s | 714 | 250 | 26,083 | |
| Gemini 3.1 Pro Preview | 10.0 | 10.0 | 100.0% | 0 | 11.77s | 490 | 108 | 1,179 |
| 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 | 10.0 | 10.0 | 100.0% | 0 | 6.22s | 921 | 99 | 5,965 | |
| Gemini 3.1 Pro Preview | 10.0 | 10.0 | 100.0% | 0 | 9.56s | 621 | 72 | 2,236 |
| 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 | 10.0 | 10.0 | 100.0% | 0 | 16.54s | 912 | 716 | 29,419 | |
| Gemini 3.1 Pro Preview | 10.0 | 10.0 | 100.0% | 0 | 6.90s | 570 | 235 | 3,128 |
| 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 | 9.86s | 11,757 | 355 | 3,989 | |
| Gemini 3.1 Pro Preview | 10.0 | 10.0 | 100.0% | 0 | 23.15s | 6,018 | 274 | 982 |
| 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 | 18.80s | 264 | 276 | 10,306 | |
| Gemini 3.1 Pro Preview | 10.0 | 10.0 | 100.0% | 0 | 6.27s | 156 | 12 | 1,297 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
Gemini 3.1 Pro PreviewmediumvsInklinghighTersedia gratisGemini 3.1 Pro PreviewmediumvsMuse Glimmer 30BxhighGemini 3.1 Pro PreviewmediumvsMuse Spark 1.1highClaude Haiku 5.5maxvsQwen3.7 MaxmediumGemini 3.1 Pro PreviewmediumvsQwen3.8 2.4T A95BlowClaude Haiku 5.5maxvsMuse Spark 1.3lowDeepSeek V4 Flash 0731highvsGemini 3.1 Pro PreviewmediumClaude Haiku 5.5maxvsGrok 4.6highClaude Haiku 5.5maxvsQwen3.8 2.4T A95BlowGemini 3.1 Pro PreviewmediumvsGLM 5.2highClaude Haiku 5.5maxvsGPT-5 MinimediumClaude Haiku 5.5maxvsMuse Glimmer 30Bxhigh