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: Responstijd (gem.) ↓.
| Rang | Model | Bedrijf | Gegevensparsering en extractie-score | Score | Correcte tests | Responstijd (gem.) |
|---|---|---|---|---|---|---|
| #40 | Gemini 3.1 Flash Lite Preview medium | 10.0 | 7.5 | 2/2 | 2.29s | |
| #57 | Step 3.7 Flash low | Stepfun | 7.3 | 7.3 | 1/2 | 2.29s |
| #85 | Gemma 4 31B none | 10.0 | 6.5 | 2/2 | 2.25s | |
| #63 | GPT-5.3 Chat none | OpenAI | 10.0 | 7.2 | 2/2 | 2.21s |
| #8 | Claude Opus 4.7 none | Anthropic | 10.0 | 8.9 | 2/2 | 2.15s |
| #128 | Qwen3.6 Flash none | Qwen | 10.0 | 5.4 | 2/2 | 2.13s |
| #118 | Qwen3.6 27B none | Qwen | 7.3 | 5.6 | 1/2 | 2.06s |
| #99 | gpt-oss-120b medium | OpenAI | 6.4 | 6.1 | 1/2 | 1.98s |
| #104 | Nemotron 3 Ultra 550b A55b none | NVIDIA | 10.0 | 6.0 | 2/2 | 1.94s |
| #95 | Qwen3.5 Plus 2026-02-15 none | Qwen | 10.0 | 6.3 | 2/2 | 1.89s |
| #110 | Seed-2.0-Lite none | Bytedance Seed | 10.0 | 5.8 | 2/2 | 1.82s |
| #3 | Gemini 3.5 Flash low | 10.0 | 9.4 | 2/2 | 1.81s | |
| #68 | Claude Opus 4.8 none | Anthropic | 7.3 | 7.0 | 1/2 | 1.77s |
| #101 | Mimo V2 Omni none | Xiaomi | 10.0 | 6.0 | 2/2 | 1.76s |
| #102 | Gemma 4 26B A4B none | 10.0 | 6.0 | 2/2 | 1.70s |