AI BENCHY Compare
Google: Gemini 2.5 Flash vs OpenAI: gpt-oss-120b
Vergelijken:
Benchmarks gegenereerd uit AI BENCHY-testsuites op: 2026-03-03
| Metriek | Google: Gemini 2.5 Flash none Releasedatum: 2025-06-17 | OpenAI: gpt-oss-120b medium Releasedatum: 2025-08-05 Gratis beschikbaar |
|---|---|---|
| Rang | #36 | #34 |
| Gem. score | 5.34 | 5.64 |
| Consistentie | 9.40 | 7.55 |
| Kosten per resultaat | 0.107 | 0.101 |
| Totale kosten | $0.007 | $0.008 |
| Correcte tests | ||
| Slaagpercentage per poging | 47.6% | 59.5% |
| Instabiele tests | 1 | 4 |
| Uitvoer-tokens | 826 | 11,407 |
| Redeneer-tokens | 0 | 26,106 |
Score vs totale kosten
Categorie-uitsplitsing
| Anti-AI-trucs | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|
| Google: Gemini 2.5 Flash | 1.00 | 10.00 | 0.0% | 0 | 99 | 0 | |
| OpenAI: gpt-oss-120b | 7.00 | 9.81 | 66.7% | 0 | 3,463 | 2,077 |
| Gegevensparsering en extractie | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|
| Google: Gemini 2.5 Flash | 9.88 | 10.00 | 100.0% | 0 | 279 | 0 | |
| OpenAI: gpt-oss-120b | 5.50 | 5.87 | 66.7% | 1 | 241 | 1,114 |
| Domeinspecifiek | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|
| Google: Gemini 2.5 Flash | 4.00 | 7.21 | 55.6% | 1 | 12 | 0 | |
| OpenAI: gpt-oss-120b | 1.00 | 4.41 | 22.2% | 2 | 6,018 | 18,520 |
| Instructies opvolgen | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|
| Google: Gemini 2.5 Flash | 8.00 | 9.99 | 50.0% | 0 | 70 | 0 | |
| OpenAI: gpt-oss-120b | 10.00 | 10.00 | 100.0% | 0 | 120 | 1,770 |
| Puzzle Solving | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|
| Google: Gemini 2.5 Flash | 4.67 | 10.00 | 33.3% | 0 | 132 | 0 | |
| OpenAI: gpt-oss-120b | 5.00 | 7.13 | 44.4% | 1 | 1,278 | 1,542 |
| Toolaanroepen | Score | Consistentie | Slaagpercentage per poging | Instabiele tests | Correcte tests | Uitvoer-tokens | Redeneer-tokens |
|---|---|---|---|---|---|---|---|
| Google: Gemini 2.5 Flash | 10.00 | 10.00 | 100.0% | 0 | 234 | 0 | |
| OpenAI: gpt-oss-120b | 9.00 | 9.97 | 100.0% | 0 | 287 | 1,083 |
Snelle vergelijking
Vergelijkingspaar wisselen
Gemini 2.5 FlashnonevsMiniMax M2.5mediumgpt-oss-120bmediumGratis beschikbaarvsGLM 5noneGemini 2.5 FlashnonevsGPT-5 MinimediumGemini 2.5 FlashnonevsQwen3.5-Flashmediumgpt-oss-120bmediumGratis beschikbaarvsQwen3.5-122B-A10BnoneGemini 2.5 FlashnonevsGPT-5 NanomediumGemini 2.5 FlashnonevsQwen3.5-35B-A3Bmediumgpt-oss-120bmediumGratis beschikbaarvsQwen3.5 Plus 2026-02-15noneGemini 2.5 FlashnonevsMiMo-V2-FlashmediumClaude Sonnet 4.6nonevsgpt-oss-120bmediumGratis beschikbaarClaude Opus 4.6mediumvsGemini 2.5 FlashnoneSeed-2.0-MinimediumvsGemini 2.5 Flashnone