AI BENCHY Compare
DeepSeek: DeepSeek V3.2 vs Qwen: Qwen3.5-122B-A10B
Benchmarks gegenereerd uit AI BENCHY-testsuites op: 2026-03-03
| Metriek | DeepSeek: DeepSeek V3.2 medium Releasedatum: 2025-12-01 | Qwen: Qwen3.5-122B-A10B medium Releasedatum: 2026-02-24 |
|---|---|---|
| Rang | #12 | #14 |
| Gem. score | 6.98 | 6.77 |
| Consistentie | 8.75 | 8.22 |
| Kosten per resultaat | 0.193 | 5.137 |
| Totale kosten | $0.018 | $0.463 |
| Correcte tests | 9/14 | 9/14 |
| Slaagpercentage per poging | 71.4% | 76.2% |
| Instabiele tests | 2 | 3 |
| Uitvoer-tokens | 6,753 | 16,751 |
| Redeneer-tokens | 30,427 | 125,394 |
Categorie-uitsplitsing
| Anti-AI-trucs | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 7.00 | 9.86 | 66.7% | 0 | 1,171 | 4,893 | |
| Qwen: Qwen3.5-122B-A10B | 10.00 | 10.00 | 100.0% | 0 | 248 | 10,486 |
| Gegevensparsering en extractie | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 9.88 | 10.00 | 100.0% | 0 | 207 | 7,693 | |
| Qwen: Qwen3.5-122B-A10B | 9.88 | 10.00 | 100.0% | 0 | 270 | 16,558 |
| Domeinspecifiek | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 4.00 | 7.21 | 44.4% | 1 | 3,081 | 7,856 | |
| Qwen: Qwen3.5-122B-A10B | 1.00 | 7.21 | 11.1% | 1 | 15,537 | 64,889 |
| Instructies opvolgen | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 7.00 | 9.84 | 50.0% | 0 | 1,397 | 2,845 | |
| Qwen: Qwen3.5-122B-A10B | 5.50 | 5.92 | 83.3% | 1 | 77 | 7,372 |
| Puzzle Solving | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 7.00 | 7.21 | 88.9% | 1 | 390 | 6,281 | |
| Qwen: Qwen3.5-122B-A10B | 7.00 | 7.21 | 88.9% | 1 | 297 | 24,863 |
| 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 | 507 | 859 | |
| Qwen: Qwen3.5-122B-A10B | 10.00 | 10.00 | 100.0% | 0 | 322 | 1,226 |
Snelle vergelijking
Vergelijkingspaar wisselen
DeepSeek V3.2mediumvsGemini 3 Flash PreviewnoneClaude Sonnet 4.6nonevsQwen3.5-122B-A10BmediumGemini 3 Flash PreviewnonevsQwen3.5-122B-A10BmediumClaude Sonnet 4.6nonevsDeepSeek V3.2mediumDeepSeek V3.2mediumvsQwen3.5 Plus 2026-02-15noneQwen3.5-122B-A10BmediumvsGLM 5noneDeepSeek V3.2mediumvsGLM 5noneDeepSeek V3.2mediumvsGemini 3 Flash PreviewlowGemini 3 Flash PreviewlowvsQwen3.5-122B-A10BmediumDeepSeek V3.2mediumvsQwen3.5-122B-A10BnoneGPT-4o-mininonevsQwen3.5-122B-A10BmediumDeepSeek V3.2nonevsQwen3.5-122B-A10Bmedium