AI BENCHY Categorie
Gegevensparsering en extractie-ranglijst
Zie welke AI-modellen het best presteren op Gegevensparsering en extractie, welke betrouwbaar blijven en waar de grootste verschillen zitten. Sorteren op: Metriek ↑.
| Rang | Model | Bedrijf | Gegevensparsering en extractie-score | Score | Correcte tests | Responstijd (gem.) |
|---|---|---|---|---|---|---|
| #81 | Mercury 2 medium | Inception | 7.3 | 6.6 | 1/2 | 1.11s |
| #103 | DeepSeek V4 Pro high | DeepSeek | 7.3 | 6.0 | 1/2 | 23.6s |
| #132 | Mistral Small 4 medium | Mistral | 7.3 | 5.3 | 1/2 | 1.23s |
| #149 | Nemotron 3 Nano Omni 30b A3b Reasoning medium | NVIDIA | 7.3 | 4.6 | 1/2 | 2.72s |
| #155 | Mercury 2 none | Inception | 7.3 | 4.5 | 1/2 | 667ms |
| #1 | Gemini 3 Flash Preview medium | 10.0 | 9.8 | 2/2 | 5.43s | |
| #2 | Gemini 3.5 Flash high | 10.0 | 9.6 | 2/2 | 6.43s | |
| #3 | Gemini 3.5 Flash low | 10.0 | 9.4 | 2/2 | 1.81s | |
| #4 | Gemini 3.1 Pro Preview medium | 10.0 | 9.4 | 2/2 | 7.72s | |
| #5 | Qwen3.7 Max medium | Qwen | 10.0 | 9.1 | 2/2 | 8.80s |
| #6 | GPT-5.5 low | OpenAI | 10.0 | 9.0 | 2/2 | 3.28s |
| #7 | Gemini 3.5 Flash medium | 10.0 | 9.0 | 2/2 | 4.07s | |
| #8 | Claude Opus 4.7 none | Anthropic | 10.0 | 8.9 | 2/2 | 2.15s |
| #9 | GPT-5.5 medium | OpenAI | 10.0 | 8.8 | 2/2 | 4.18s |
| #11 | Claude Opus 4.7 medium | Anthropic | 10.0 | 8.7 | 2/2 | 2.37s |