AI BENCHY Compare
OpenAI: GPT-5.4 vs Qwen: Qwen3.5-35B-A3B
Bandingkan:
Benchmark dihasilkan dari suite pengujian AI BENCHY pada: 2026-03-05
| Metrik | OpenAI: GPT-5.4 none Rilis: 2026-03-05 | Qwen: Qwen3.5-35B-A3B none Rilis: 2026-02-24 |
|---|---|---|
| Peringkat | #44 | #43 |
| Skor Rata-rata | 4.6 | 4.7 |
| Tes benar | ||
| Konsistensi | 8.9 | 8.9 |
| Biaya per hasil | 1.496 | 0.233 |
| Total Biaya | $0.090 | $0.014 |
| Tingkat lulus per percobaan | 44.4% | 48.9% |
| Tes tidak stabil | 2 | 2 |
| common.totalAttempts | 45 (15 x 3) | 45 (15 x 3) |
| Token output | 1,635 | 3,642 |
| Token penalaran | 0 | 0 |
| Waktu respons (rata-rata) | 1.46s | 4.30s |
| Waktu respons (maks) | 2.89s | 47.43s |
| Waktu respons (total) | 21.86s | 64.43s |
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 |
|---|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5.4 | 10.0 | 7.3 | 11.1% | 1 | 1.41s | 388 | 0 | |
| Qwen: Qwen3.5-35B-A3B | 10.0 | 7.2 | 22.2% | 1 | 1.76s | 569 | 0 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5.4 | 10.0 | 10.0 | 0.0% | 0 | 2.89s | 291 | 0 | |
| Qwen: Qwen3.5-35B-A3B | 10.0 | 10.0 | 0.0% | 0 | 47.43s | 1,833 | 0 |
| Parsing dan ekstraksi data | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5.4 | 9.9 | 10.0 | 100.0% | 0 | 1.04s | 222 | 0 | |
| Qwen: Qwen3.5-35B-A3B | 9.9 | 10.0 | 100.0% | 0 | 1.16s | 243 | 0 |
| Spesifik domain | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5.4 | 4.0 | 7.2 | 44.4% | 1 | 1.07s | 50 | 0 | |
| Qwen: Qwen3.5-35B-A3B | 7.0 | 10.0 | 66.7% | 0 | 485ms | 15 | 0 |
| Kepatuhan instruksi | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5.4 | 5.5 | 10.0 | 50.0% | 0 | 1.07s | 81 | 0 | |
| Qwen: Qwen3.5-35B-A3B | 5.0 | 10.0 | 50.0% | 0 | 809ms | 63 | 0 |
| Puzzle Solving | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5.4 | 4.0 | 9.8 | 33.3% | 0 | 1.52s | 357 | 0 | |
| Qwen: Qwen3.5-35B-A3B | 1.7 | 7.4 | 22.2% | 1 | 1.34s | 655 | 0 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5.4 | 10.0 | 10.0 | 100.0% | 0 | 2.75s | 246 | 0 | |
| Qwen: Qwen3.5-35B-A3B | 10.0 | 10.0 | 100.0% | 0 | 2.30s | 264 | 0 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
MiniMax M2.5mediumvsQwen3.5-35B-A3BnoneMiniMax M2.5mediumvsGPT-5.4nonegpt-oss-120bmediumTersedia gratisvsQwen3.5-35B-A3BnoneMercury 2mediumvsQwen3.5-35B-A3BnoneMercury 2mediumvsGPT-5.4noneGPT-5 NanomediumvsQwen3.5-35B-A3BnoneGPT-5.4nonevsQwen3.5-35B-A3BmediumGPT-5.4nonevsQwen3 Coder NextmediumGPT-5.4nonevsGLM 4.7 FlashmediumGPT-5 MinimediumvsQwen3.5-35B-A3BnoneQwen3.5-35B-A3BnonevsGLM 4.7 FlashmediumClaude Opus 4.6mediumvsQwen3.5-35B-A3Bnone