AI BENCHY Compare
DeepSeek: DeepSeek V3.2 vs OpenAI: GPT-4o-mini
Benchmark dihasilkan dari suite pengujian AI BENCHY pada: 2026-03-03
| Metrik | DeepSeek: DeepSeek V3.2 medium Rilis: 2025-12-01 | OpenAI: GPT-4o-mini none Rilis: 2024-07-18 |
|---|---|---|
| Peringkat | #12 | #29 |
| Skor Rata-rata | 6.98 | 4.86 |
| Konsistensi | 8.75 | 9.98 |
| Biaya per hasil | 0.193 | 0.056 |
| Total Biaya | $0.018 | $0.003 |
| Tes benar | 9/14 | 5/14 |
| Tingkat lulus per percobaan | 71.4% | 35.7% |
| Tes tidak stabil | 2 | 0 |
| Token output | 6,753 | 949 |
| Token penalaran | 30,427 | 0 |
Rincian Kategori
| Trik anti-AI | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 7.00 | 9.86 | 66.7% | 0 | 1,171 | 4,893 | |
| OpenAI: GPT-4o-mini | 4.00 | 10.00 | 33.3% | 0 | 180 | 0 |
| Parsing dan ekstraksi data | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 9.88 | 10.00 | 100.0% | 0 | 207 | 7,693 | |
| OpenAI: GPT-4o-mini | 10.00 | 10.00 | 100.0% | 0 | 183 | 0 |
| Spesifik domain | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 4.00 | 7.21 | 44.4% | 1 | 3,081 | 7,856 | |
| OpenAI: GPT-4o-mini | 1.00 | 10.00 | 0.0% | 0 | 15 | 0 |
| Kepatuhan instruksi | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 7.00 | 9.84 | 50.0% | 0 | 1,397 | 2,845 | |
| OpenAI: GPT-4o-mini | 5.50 | 10.00 | 50.0% | 0 | 71 | 0 |
| Puzzle Solving | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 7.00 | 7.21 | 88.9% | 1 | 390 | 6,281 | |
| OpenAI: GPT-4o-mini | 4.00 | 9.92 | 0.0% | 0 | 295 | 0 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 10.00 | 10.00 | 100.0% | 0 | 507 | 859 | |
| OpenAI: GPT-4o-mini | 10.00 | 10.00 | 100.0% | 0 | 205 | 0 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
DeepSeek V3.2mediumvsGemini 3 Flash PreviewnoneClaude Sonnet 4.6nonevsDeepSeek V3.2mediumDeepSeek V3.2mediumvsQwen3.5 Plus 2026-02-15noneGPT-4o-mininonevsGLM 4.7 FlashmediumMiniMax M2.5mediumvsGPT-4o-mininoneDeepSeek V3.2mediumvsGLM 5noneGPT-4o-mininonevsQwen3.5-FlashmediumGPT-4o-mininonevsQwen3.5-35B-A3BmediumGPT-4o-mininonevsMiMo-V2-FlashmediumClaude Opus 4.6mediumvsGPT-4o-mininoneSeed-2.0-MinimediumvsGPT-4o-mininoneGPT-4o-mininonevsQwen3 Coder Nextmedium