AI BENCHY Compare
Anthropic: Claude Sonnet 4.6 vs OpenAI: GPT-5 Mini
Vergelijken:
Benchmarks gegenereerd uit AI BENCHY-testsuites op: 2026-03-03
| Metriek | Anthropic: Claude Sonnet 4.6 none Releasedatum: 2026-02-17 | OpenAI: GPT-5 Mini medium Releasedatum: 2025-08-07 |
|---|---|---|
| Rang | #22 | #33 |
| Gem. score | 6.36 | 5.77 |
| Consistentie | 9.50 | 8.79 |
| Kosten per resultaat | 1.325 | 1.200 |
| Totale kosten | $0.106 | $0.084 |
| Correcte tests | ||
| Slaagpercentage per poging | 59.5% | 57.1% |
| Instabiele tests | 1 | 2 |
| Uitvoer-tokens | 2,637 | 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 |
|---|---|---|---|---|---|---|---|
| Anthropic: Claude Sonnet 4.6 | 4.00 | 10.00 | 33.3% | 0 | 1,199 | 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 |
|---|---|---|---|---|---|---|---|
| Anthropic: Claude Sonnet 4.6 | 10.00 | 10.00 | 100.0% | 0 | 252 | 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 |
|---|---|---|---|---|---|---|---|
| Anthropic: Claude Sonnet 4.6 | 7.00 | 10.00 | 66.7% | 0 | 54 | 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 |
|---|---|---|---|---|---|---|---|
| Anthropic: Claude Sonnet 4.6 | 5.50 | 10.00 | 50.0% | 0 | 90 | 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 |
|---|---|---|---|---|---|---|---|
| Anthropic: Claude Sonnet 4.6 | 5.00 | 7.68 | 44.4% | 1 | 595 | 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 |
|---|---|---|---|---|---|---|---|
| Anthropic: Claude Sonnet 4.6 | 10.00 | 10.00 | 100.0% | 0 | 447 | 0 | |
| OpenAI: GPT-5 Mini | 10.00 | 10.00 | 100.0% | 0 | 487 | 1,600 |
Snelle vergelijking
Vergelijkingspaar wisselen
Claude Sonnet 4.6nonevsGrok 4.1 FastmediumClaude Sonnet 4.6nonevsKimi K2.5mediumClaude Sonnet 4.6nonevsSeed-2.0-MinimediumGPT-5 MinimediumvsGLM 5noneClaude Sonnet 4.6nonevsMiMo-V2-FlashmediumClaude Sonnet 4.6nonevsQwen3.5-122B-A10BmediumClaude Sonnet 4.6nonevsQwen3.5-35B-A3BmediumGemini 2.5 FlashnonevsGPT-5 MinimediumClaude Sonnet 4.6nonevsGPT-5 NanomediumGPT-5 MinimediumvsQwen3.5 Plus 2026-02-15noneClaude Sonnet 4.6nonevsGemini 3.1 Flash Lite PreviewmediumClaude Sonnet 4.6nonevsQwen3.5-Flashmedium