AI BENCHY Compare
DeepSeek: DeepSeek V3.2 vs Z.ai: GLM 5
Benchmarks gegenereerd uit AI BENCHY-testsuites op: 2026-03-03
| Metriek | DeepSeek: DeepSeek V3.2 medium Releasedatum: 2025-12-01 | Z.ai: GLM 5 medium Releasedatum: 2026-02-12 |
|---|---|---|
| Rang | #12 | #9 |
| Gem. score | 6.98 | 7.29 |
| Consistentie | 8.75 | 8.18 |
| Kosten per resultaat | 0.193 | 1.196 |
| Totale kosten | $0.018 | $0.120 |
| Correcte tests | 9/14 | 10/14 |
| Slaagpercentage per poging | 71.4% | 83.3% |
| Instabiele tests | 2 | 3 |
| Uitvoer-tokens | 6,753 | 15,923 |
| Redeneer-tokens | 30,427 | 42,557 |
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 | |
| Z.ai: GLM 5 | 10.00 | 10.00 | 100.0% | 0 | 420 | 4,992 |
| 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 | |
| Z.ai: GLM 5 | 5.00 | 5.62 | 83.3% | 1 | 567 | 3,734 |
| 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 | |
| Z.ai: GLM 5 | 1.00 | 4.41 | 33.3% | 2 | 14,404 | 24,570 |
| 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 | |
| Z.ai: GLM 5 | 9.50 | 9.99 | 100.0% | 0 | 140 | 2,740 |
| 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 | |
| Z.ai: GLM 5 | 10.00 | 10.00 | 100.0% | 0 | 159 | 5,527 |
| 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 | |
| Z.ai: GLM 5 | 10.00 | 10.00 | 100.0% | 0 | 233 | 994 |
Snelle vergelijking
Vergelijkingspaar wisselen
Gemini 3 Flash PreviewnonevsGLM 5mediumDeepSeek V3.2mediumvsGemini 3 Flash PreviewnoneClaude Sonnet 4.6nonevsDeepSeek V3.2mediumDeepSeek V3.2mediumvsQwen3.5 Plus 2026-02-15noneDeepSeek V3.2mediumvsGLM 5noneClaude Sonnet 4.6nonevsGLM 5mediumQwen3.5 Plus 2026-02-15nonevsGLM 5mediumGemini 3 Flash PreviewlowvsGLM 5mediumDeepSeek V3.2mediumvsGemini 3 Flash PreviewlowDeepSeek V3.2mediumvsQwen3.5-122B-A10BnoneQwen3.5-122B-A10BnonevsGLM 5mediumDeepSeek V3.2mediumvsGPT-4o-mininone