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.) ↑.
Getoonde modellen
15
Gemiddelde Gegevensparsering en extractie-score
8.7
Beste model
MiMo-V2-Flash 6.5| Rang | Model | Bedrijf | Gegevensparsering en extractie-score | Score | Correcte tests | Responstijd (gem.) |
|---|---|---|---|---|---|---|
| #138 | Ling-2.6-flash none | Inclusionai | 6.5 | 5.0 | 1/2 | 8.48s |
| #116 | Hunter Alpha none | OpenRouter | 10.0 | 5.7 | 2/2 | 8.49s |
| #5 | Qwen3.7 Max medium | Qwen | 10.0 | 9.1 | 2/2 | 8.80s |
| #17 | GLM 5 medium | Z.ai | 7.1 | 8.3 | 1/2 | 8.90s |
| #19 | Seed-2.0-Lite medium | Bytedance Seed | 10.0 | 8.2 | 2/2 | 9.07s |
| #100 | Grok Build 0.1 none | X AI | 3.8 | 6.0 | 0/2 | 9.33s |
| #55 | GLM 5.1 medium | Z.ai | 10.0 | 7.3 | 2/2 | 9.33s |
| #107 | Laguna Xs.2 medium | Poolside | 7.1 | 5.8 | 1/2 | 9.34s |
| #16 | Gemini 3 Flash Preview low | 10.0 | 8.4 | 2/2 | 9.40s | |
| #133 | DeepSeek V3.2 none | DeepSeek | 6.3 | 5.2 | 1/2 | 9.42s |
| #59 | GLM 5V Turbo medium | Z.ai | 10.0 | 7.2 | 2/2 | 9.60s |
| #39 | Qwen3.6 Flash medium | Qwen | 10.0 | 7.5 | 2/2 | 9.65s |
| #47 | Grok Build 0.1 medium | X AI | 10.0 | 7.4 | 2/2 | 10.7s |
| #35 | Gemini 3 PRO Preview medium | 10.0 | 7.6 | 2/2 | 10.8s | |
| #82 | Hy3 preview high | Tencent | 6.5 | 6.6 | 1/2 | 12.1s |