AI BENCHY Compare
Google: Gemini 3 Flash Preview vs OpenAI: GPT-5 Mini
Vergelijken:
Benchmarks gegenereerd uit AI BENCHY-testsuites op: 2026-03-04
| Metriek | Google: Gemini 3 Flash Preview none Releasedatum: 2025-12-17 | OpenAI: GPT-5 Mini medium Releasedatum: 2025-08-07 |
|---|---|---|
| Rang | #15 | #33 |
| Gem. score | 7.21 | 5.77 |
| Consistentie | 9.36 | 8.79 |
| Kosten per resultaat | 0.078 | 1.200 |
| Totale kosten | $0.007 | $0.084 |
| Correcte tests | ||
| Slaagpercentage per poging | 71.8% | 57.1% |
| Instabiele tests | 1 | 2 |
| Uitvoer-tokens | 734 | 4,723 |
| Redeneer-tokens | 0 | 35,392 |
Score vs totale kosten
Categorie-uitsplitsing
| Anti-AI-trucs | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|
| Google: Gemini 3 Flash Preview | 7.00 | 10.00 | 66.7% | 0 | 240 | 0 | |
| OpenAI: GPT-5 Mini | 7.00 | 9.62 | 66.7% | 0 | 1,645 | 5,824 |
| Gegevensparsering en extractie | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|
| Google: Gemini 3 Flash Preview | 9.88 | 10.00 | 100.0% | 0 | 279 | 0 | |
| OpenAI: GPT-5 Mini | 9.88 | 10.00 | 100.0% | 0 | 453 | 3,200 |
| Domeinspecifiek | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|
| Google: Gemini 3 Flash Preview | 7.00 | 10.00 | 66.7% | 0 | 18 | 0 | |
| OpenAI: GPT-5 Mini | 1.00 | 7.21 | 22.2% | 1 | 293 | 14,016 |
| Instructies opvolgen | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|
| Google: Gemini 3 Flash Preview | 5.50 | 5.81 | 66.7% | 1 | 74 | 0 | |
| OpenAI: GPT-5 Mini | 7.00 | 6.64 | 66.7% | 1 | 318 | 4,992 |
| Puzzle Solving | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|
| Google: Gemini 3 Flash Preview | 7.00 | 10.00 | 66.7% | 0 | 123 | 0 | |
| OpenAI: GPT-5 Mini | 4.33 | 9.78 | 33.3% | 0 | 1,527 | 5,760 |
| Toolaanroepen | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|
| Google: Gemini 3 Flash Preview | - | - | - | - | - | - | - |
| OpenAI: GPT-5 Mini | 10.00 | 10.00 | 100.0% | 0 | 487 | 1,600 |
Snelle vergelijking
Vergelijkingspaar wisselen
Gemini 3 Flash PreviewnonevsGLM 5mediumGemini 3 Flash PreviewnonevsStep 3.5 FlashmediumGratis beschikbaarClaude Sonnet 4.6mediumvsGemini 3 Flash PreviewnoneDeepSeek V3.2mediumvsGemini 3 Flash PreviewnoneGemini 3 Flash PreviewnonevsGPT-5.2mediumGPT-5 MinimediumvsGLM 5noneGemini 2.5 FlashnonevsGPT-5 MinimediumGemini 3 Flash PreviewnonevsQwen3.5-122B-A10BmediumGPT-5 MinimediumvsQwen3.5 Plus 2026-02-15noneGPT-5 MinimediumvsQwen3.5-122B-A10BnoneClaude Sonnet 4.6nonevsGPT-5 MinimediumGemini 3 Flash PreviewnonevsGPT-5.3-Codexmedium