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.) |
|---|---|---|---|---|---|---|
| #142 | Mistral Small 4 none | Mistral | 10.0 | 4.9 | 2/2 | 822ms |
| #144 | GPT-5.4 Mini none | OpenAI | 10.0 | 4.9 | 2/2 | 1.30s |
| #145 | Laguna M.1 none | Poolside | 10.0 | 4.8 | 2/2 | 3.37s |
| #146 | Laguna Xs.2 none | Poolside | 10.0 | 4.8 | 2/2 | 646ms |
| #147 | GPT-4o-mini none | OpenAI | 10.0 | 4.8 | 2/2 | 1.27s |
| #151 | Trinity Large Preview none | Arcee AI | 10.0 | 4.6 | 2/2 | 3.26s |
| #153 | Qwen3.6 35B A3B none | Qwen | 10.0 | 4.6 | 2/2 | 1.46s |
| #154 | Qwen3.5-9B none | Qwen | 10.0 | 4.6 | 2/2 | 847ms |
| #157 | Grok 4.1 Fast none | X AI | 10.0 | 4.4 | 2/2 | 943ms |
| #159 | Ling-2.6-1T none | Inclusionai | 10.0 | 4.3 | 2/2 | 1.37s |
| #31 | DeepSeek V4 Flash high | DeepSeek | 10.0 | 7.7 | 2/2 | 28.0s |
| #62 | Step 3.5 Flash medium | Stepfun | 10.0 | 7.2 | 2/2 | 15.0s |
| #139 | DeepSeek V4 Flash none | DeepSeek | 10.0 | 5.0 | 2/2 | 23.8s |