AI BENCHY Compare
DeepSeek: DeepSeek V3.2 vs Xiaomi: MiMo-V2-Flash
Benchmarks gegenereerd uit AI BENCHY-testsuites op: 2026-03-03
| Metriek | DeepSeek: DeepSeek V3.2 none Releasedatum: 2025-12-01 | Xiaomi: MiMo-V2-Flash medium Releasedatum: 2025-12-16 |
|---|---|---|
| Rang | #30 | #22 |
| Gem. score | 4.70 | 6.00 |
| Consistentie | 8.19 | 8.79 |
| Kosten per resultaat | 0.132 | 0.364 |
| Totale kosten | $0.007 | $0.030 |
| Correcte tests | 5/14 | 8/14 |
| Slaagpercentage per poging | 47.6% | 64.3% |
| Instabiele tests | 3 | 2 |
| Uitvoer-tokens | 4,869 | 11,650 |
| Redeneer-tokens | 0 | 93,283 |
Categorie-uitsplitsing
| Anti-AI-trucs | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 1.00 | 9.68 | 0.0% | 0 | 1,411 | 0 | |
| Xiaomi: MiMo-V2-Flash | 9.67 | 9.99 | 100.0% | 0 | 1,328 | 18,739 |
| Gegevensparsering en extractie | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 5.38 | 5.81 | 66.7% | 1 | 1,710 | 0 | |
| Xiaomi: MiMo-V2-Flash | 5.50 | 10.00 | 50.0% | 0 | 153 | 0 |
| Domeinspecifiek | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 1.00 | 7.21 | 22.2% | 1 | 24 | 0 | |
| Xiaomi: MiMo-V2-Flash | 4.00 | 7.21 | 55.6% | 1 | 8,363 | 51,202 |
| Instructies opvolgen | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 8.00 | 9.99 | 50.0% | 0 | 66 | 0 | |
| Xiaomi: MiMo-V2-Flash | 9.50 | 9.99 | 100.0% | 0 | 72 | 3,504 |
| Puzzle Solving | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 7.67 | 7.49 | 88.9% | 1 | 1,136 | 0 | |
| Xiaomi: MiMo-V2-Flash | 1.00 | 7.14 | 11.1% | 1 | 1,413 | 7,123 |
| Toolaanroepen | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 10.00 | 10.00 | 100.0% | 0 | 522 | 0 | |
| Xiaomi: MiMo-V2-Flash | 10.00 | 10.00 | 100.0% | 0 | 321 | 12,715 |
Snelle vergelijking
Vergelijkingspaar wisselen
MiMo-V2-FlashmediumvsGLM 5noneQwen3.5 Plus 2026-02-15nonevsMiMo-V2-FlashmediumClaude Sonnet 4.6nonevsMiMo-V2-FlashmediumDeepSeek V3.2nonevsGLM 4.7 FlashmediumQwen3.5-122B-A10BnonevsMiMo-V2-FlashmediumDeepSeek V3.2nonevsMiniMax M2.5mediumDeepSeek V3.2nonevsgpt-oss-120bmediumGratis beschikbaarDeepSeek V3.2nonevsQwen3.5-FlashmediumGPT-4o-mininonevsMiMo-V2-FlashmediumDeepSeek V3.2nonevsGPT-5 NanomediumDeepSeek V3.2nonevsQwen3 Coder NextmediumGemini 3 Flash PreviewnonevsMiMo-V2-Flashmedium