AI BENCHY Compare
Arcee AI: Trinity Large Preview (free) vs DeepSeek: DeepSeek V3.2
Benchmark dihasilkan dari suite pengujian AI BENCHY pada: 2026-03-03
| Metrik | Arcee AI: Trinity Large Preview (free) none Rilis: 2026-01-27 Tersedia gratis | DeepSeek: DeepSeek V3.2 medium Rilis: 2025-12-01 |
|---|---|---|
| Peringkat | #33 | #12 |
| Skor Rata-rata | 4.34 | 6.98 |
| Konsistensi | 9.97 | 8.75 |
| Biaya per hasil | 0.000 | 0.193 |
| Total Biaya | $0.000 | $0.018 |
| Tes benar | 5/14 | 9/14 |
| Tingkat lulus per percobaan | 35.7% | 71.4% |
| Tes tidak stabil | 0 | 2 |
| Token output | 1,415 | 6,753 |
| Token penalaran | 0 | 30,427 |
Rincian Kategori
| Trik anti-AI | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|
| Arcee AI: Trinity Large Preview (free) | 1.00 | 10.00 | 0.0% | 0 | 587 | 0 | |
| DeepSeek: DeepSeek V3.2 | 7.00 | 9.86 | 66.7% | 0 | 1,171 | 4,893 |
| Parsing dan ekstraksi data | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|
| Arcee AI: Trinity Large Preview (free) | 9.88 | 10.00 | 100.0% | 0 | 186 | 0 | |
| DeepSeek: DeepSeek V3.2 | 9.88 | 10.00 | 100.0% | 0 | 207 | 7,693 |
| Spesifik domain | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|
| Arcee AI: Trinity Large Preview (free) | 4.00 | 10.00 | 33.3% | 0 | 21 | 0 | |
| DeepSeek: DeepSeek V3.2 | 4.00 | 7.21 | 44.4% | 1 | 3,081 | 7,856 |
| Kepatuhan instruksi | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|
| Arcee AI: Trinity Large Preview (free) | 2.00 | 9.79 | 0.0% | 0 | 63 | 0 | |
| DeepSeek: DeepSeek V3.2 | 7.00 | 9.84 | 50.0% | 0 | 1,397 | 2,845 |
| Puzzle Solving | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|
| Arcee AI: Trinity Large Preview (free) | 4.00 | 9.99 | 33.3% | 0 | 291 | 0 | |
| DeepSeek: DeepSeek V3.2 | 7.00 | 7.21 | 88.9% | 1 | 390 | 6,281 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|
| Arcee AI: Trinity Large Preview (free) | 10.00 | 10.00 | 100.0% | 0 | 267 | 0 | |
| DeepSeek: DeepSeek V3.2 | 10.00 | 10.00 | 100.0% | 0 | 507 | 859 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
Trinity Large Preview (free)noneTersedia gratisvsGLM 4.7 FlashmediumDeepSeek V3.2mediumvsGemini 3 Flash PreviewnoneClaude Sonnet 4.6nonevsDeepSeek V3.2mediumDeepSeek V3.2mediumvsQwen3.5 Plus 2026-02-15noneTrinity Large Preview (free)noneTersedia gratisvsQwen3 Coder NextmediumDeepSeek V3.2mediumvsGLM 5noneTrinity Large Preview (free)noneTersedia gratisvsMiniMax M2.5mediumTrinity Large Preview (free)noneTersedia gratisvsgpt-oss-120bmediumTersedia gratisDeepSeek V3.2mediumvsGemini 3 Flash PreviewlowTrinity Large Preview (free)noneTersedia gratisvsQwen3.5-FlashmediumTrinity Large Preview (free)noneTersedia gratisvsGPT-5 NanomediumTrinity Large Preview (free)noneTersedia gratisvsQwen3.5-35B-A3Bmedium