AI BENCHY Compare
Google: Gemini 3 Flash Preview vs OpenAI: GPT-5.4
Vergelijken:
Benchmarks gegenereerd uit AI BENCHY-testsuites op: 2026-03-05
| Metriek | Google: Gemini 3 Flash Preview low Releasedatum: 2025-12-17 | OpenAI: GPT-5.4 medium Releasedatum: 2026-03-05 |
|---|---|---|
| Gem. score | 8.1 | 8.2 |
| Correcte tests | ||
| Rang | #8 | #7 |
| Consistentie | 9.4 | 8.9 |
| Kosten per resultaat | 0.627 | 6.533 |
| Totale kosten | $0.076 | $0.784 |
| Slaagpercentage per poging | 82.2% | 86.7% |
| Instabiele tests | 1 | 2 |
| common.totalAttempts | 45 (15 x 3) | 45 (15 x 3) |
| Uitvoer-tokens | 1,466 | 1,611 |
| Redeneer-tokens | 18,969 | 46,321 |
| Responstijd (gem.) | 6.27s | 21.06s |
| Responstijd (max) | 14.72s | 100.41s |
| Responstijd (totaal) | 94.05s | 315.95s |
Score vs totale kosten
Responstijd (gem.)
Gem. score vs Responstijd (gem.)
Categorie-uitsplitsing
| Anti-AI-trucs | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Responstijd (gem.) | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|---|
| Google: Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 3.50s | 275 | 2,476 | |
| OpenAI: GPT-5.4 | 10.0 | 10.0 | 100.0% | 0 | 5.02s | 216 | 1,466 |
| Gecombineerd | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Responstijd (gem.) | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|---|
| Google: Gemini 3 Flash Preview | 10.0 | 10.0 | 0.0% | 0 | 3.27s | 326 | 0 | |
| OpenAI: GPT-5.4 | 10.0 | 10.0 | 100.0% | 0 | 20.57s | 301 | 3,543 |
| Gegevensparsering en extractie | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Responstijd (gem.) | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|---|
| Google: Gemini 3 Flash Preview | 9.9 | 10.0 | 100.0% | 0 | 9.40s | 279 | 3,656 | |
| OpenAI: GPT-5.4 | 9.9 | 10.0 | 100.0% | 0 | 5.32s | 234 | 804 |
| Domeinspecifiek | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Responstijd (gem.) | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|---|
| Google: Gemini 3 Flash Preview | 4.0 | 7.2 | 44.4% | 1 | 8.05s | 12 | 6,410 | |
| OpenAI: GPT-5.4 | 4.0 | 7.2 | 44.4% | 1 | 74.27s | 61 | 34,748 |
| Instructies opvolgen | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Responstijd (gem.) | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|---|
| Google: Gemini 3 Flash Preview | 9.5 | 10.0 | 100.0% | 0 | 7.02s | 71 | 2,752 | |
| OpenAI: GPT-5.4 | 10.0 | 10.0 | 100.0% | 0 | 3.11s | 93 | 897 |
| Puzzle Solving | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Responstijd (gem.) | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|---|
| Google: Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 6.11s | 269 | 3,260 | |
| OpenAI: GPT-5.4 | 7.0 | 7.2 | 88.9% | 1 | 9.13s | 442 | 3,832 |
| Toolaanroepen | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Responstijd (gem.) | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|---|
| Google: Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 4.99s | 234 | 415 | |
| OpenAI: GPT-5.4 | 10.0 | 10.0 | 100.0% | 0 | 13.28s | 264 | 1,031 |
Snelle vergelijking
Vergelijkingspaar wisselen
Gemini 3 Flash PreviewlowvsQwen3.5-122B-A10BmediumGemini 3.1 Flash Lite PreviewhighvsGPT-5.4mediumGemini 3 Flash PreviewlowvsGPT-5.2 ChatnoneGemini 3 Flash PreviewlowvsQwen3.5-27BmediumDeepSeek V3.2mediumvsGemini 3 Flash PreviewlowClaude Sonnet 4.6mediumvsGemini 3 Flash PreviewlowGemini 3 Flash PreviewlowvsGPT-5.3-CodexmediumGemini 3.1 Flash Lite PreviewlowvsGPT-5.4mediumGemini 3 Flash PreviewlowvsStep 3.5 FlashmediumGratis beschikbaarGemini 3 Flash PreviewlowvsMiMo-V2-FlashmediumGemini 3 Flash PreviewlowvsGLM 5mediumGemini 3 Flash PreviewlowvsGPT-5.3 Chatnone