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 none Releasedatum: 2026-02-12 |
|---|---|---|
| Rang | #12 | #20 |
| Gem. score | 6.98 | 6.07 |
| Consistentie | 8.75 | 10.00 |
| Kosten per resultaat | 0.193 | 0.095 |
| Totale kosten | $0.018 | $0.008 |
| Correcte tests | 9/14 | 8/14 |
| Slaagpercentage per poging | 71.4% | 57.1% |
| Instabiele tests | 2 | 0 |
| Uitvoer-tokens | 6,753 | 1,086 |
| Redeneer-tokens | 30,427 | 0 |
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 | 4.00 | 10.00 | 33.3% | 0 | 272 | 0 |
| 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 | 10.00 | 10.00 | 100.0% | 0 | 230 | 0 |
| 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 | 10.00 | 0.0% | 0 | 20 | 0 |
| 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 | 10.00 | 10.00 | 100.0% | 0 | 62 | 0 |
| 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 | 6.67 | 9.99 | 66.7% | 0 | 282 | 0 |
| 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 | 220 | 0 |
Snelle vergelijking
Vergelijkingspaar wisselen
Claude Opus 4.6mediumvsGLM 5noneSeed-2.0-MinimediumvsGLM 5noneMiMo-V2-FlashmediumvsGLM 5noneQwen3.5-35B-A3BmediumvsGLM 5noneGPT-5 NanomediumvsGLM 5noneKimi K2.5mediumvsGLM 5noneGrok 4.1 FastmediumvsGLM 5noneDeepSeek V3.2mediumvsGemini 3 Flash PreviewnoneQwen3.5-FlashmediumvsGLM 5nonegpt-oss-120bmediumGratis beschikbaarvsGLM 5noneMiniMax M2.5mediumvsGLM 5noneClaude Sonnet 4.6nonevsDeepSeek V3.2medium