AI BENCHY Compare
Inception: Mercury 2 vs Qwen: Qwen3.5-35B-A3B
Bandingkan:
Benchmark dihasilkan dari suite pengujian AI BENCHY pada: 2026-03-05
| Metrik | Inception: Mercury 2 none Rilis: 2026-02-24 | Qwen: Qwen3.5-35B-A3B medium Rilis: 2026-02-24 |
|---|---|---|
| Peringkat | #50 | #33 |
| Skor Rata-rata | 34 | 58 |
| Konsistensi | 89 | 67 |
| Biaya per hasil | 0.147 | 4.189 |
| Total Biaya | $0.006 | $0.336 |
| Waktu respons (rata-rata) | 594ms | 44.84s |
| Waktu respons (maks) | 1.27s | 106.00s |
| Waktu respons (total) | 8.91s | 672.55s |
| Tes benar | ||
| Tingkat lulus per percobaan | 33.3% | 80.0% |
| Tes tidak stabil | 2 | 6 |
| Token output | 1,144 | 5,475 |
| Token penalaran | 0 | 165,513 |
Waktu respons (rata-rata)
Skor vs Total Biaya
Skor Rata-rata vs Waktu respons (rata-rata)
Rincian Kategori
| Trik anti-AI | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|
| Inception: Mercury 2 | 100 | 100 | 0.0% | 0 | 466ms | 274 | 0 | |
| Qwen: Qwen3.5-35B-A3B | 100 | 100 | 100.0% | 0 | 21.75s | 429 | 36,235 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|
| Inception: Mercury 2 | 100 | 100 | 0.0% | 0 | 606ms | 131 | 0 | |
| Qwen: Qwen3.5-35B-A3B | 100 | 16 | 66.7% | 1 | 75.34s | 775 | 12,485 |
| Parsing dan ekstraksi data | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|
| Inception: Mercury 2 | 55 | 59 | 83.3% | 1 | 667ms | 180 | 0 | |
| Qwen: Qwen3.5-35B-A3B | 55 | 59 | 83.3% | 1 | 59.33s | 235 | 19,493 |
| Spesifik domain | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|
| Inception: Mercury 2 | 40 | 72 | 44.4% | 1 | 534ms | 46 | 0 | |
| Qwen: Qwen3.5-35B-A3B | 100 | 44 | 44.5% | 2 | 88.34s | 41 | 46,368 |
| Kepatuhan instruksi | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|
| Inception: Mercury 2 | 55 | 100 | 50.0% | 0 | 551ms | 82 | 0 | |
| Qwen: Qwen3.5-35B-A3B | 100 | 100 | 100.0% | 0 | 24.45s | 97 | 17,361 |
| Puzzle Solving | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|
| Inception: Mercury 2 | 100 | 100 | 0.0% | 0 | 533ms | 234 | 0 | |
| Qwen: Qwen3.5-35B-A3B | 40 | 44 | 77.8% | 2 | 31.58s | 3,589 | 32,206 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|
| Inception: Mercury 2 | 100 | 100 | 100.0% | 0 | 1.27s | 197 | 0 | |
| Qwen: Qwen3.5-35B-A3B | 100 | 100 | 100.0% | 0 | 4.65s | 309 | 1,365 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
Qwen3.5-35B-A3BmediumvsGLM 5noneMercury 2nonevsQwen3 Coder NextmediumMercury 2nonevsGLM 4.7 FlashmediumGemini 2.5 FlashnonevsQwen3.5-35B-A3BmediumDeepSeek V3.2nonevsQwen3.5-35B-A3BmediumClaude Sonnet 4.6nonevsQwen3.5-35B-A3BmediumGemini 3 Flash PreviewnonevsQwen3.5-35B-A3BmediumGPT-5.4nonevsQwen3.5-35B-A3BmediumMercury 2nonevsMiniMax M2.5mediumTrinity Large Preview (free)noneTersedia gratisvsQwen3.5-35B-A3BmediumGemini 3.1 Flash Lite PreviewnonevsQwen3.5-35B-A3BmediumGPT-4o-mininonevsQwen3.5-35B-A3Bmedium