OCRBench
Ergebnisse von KI-Benchmarks und Modellleistung
Typ: percentageImage To Text
Erfasste Ergebnisse
50
Durchschnittspunktzahl
559%
Punktzahlbereich
80.90% - 920%
Führendes Modell
920% - Qwen 3 VL 235B A22B Instruct
Punktzahlen im Zeitverlauf
Einzelne Benchmark-Punktzahlen nach Datum.
Modellergebnisse
| Organisation | Modelle | Gemeldet am | Höchste Punktzahl | Info | Selbst gemeldet | Quelle |
|---|---|---|---|---|---|---|
| Qwen 3 VL 235B A22B Instruct | - | 920 % | - | Ja | - | |
| Qwen 3 VL 30B A3B Instruct | - | 903 % | - | Ja | - | |
| Qwen 3 VL 8B Instruct | - | 896 % | - | Ja | - | |
| Qwen 3 VL 32B Instruct | - | 895 % | - | Ja | - | |
| Qwen 3 VL 4B Instruct | - | 881 % | - | Ja | - | |
| Qwen 3 VL 235B A22B Thinking | - | 875 % | - | Ja | - | |
| Qwen 3 VL 32B Thinking | - | 855 % | - | Ja | - | |
| Qwen 3 VL 30B A3B Thinking | - | 839 % | - | Ja | - | |
| Qwen 3 8B | - | 819 % | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.4600; benches=50) | Ja | - | |
| Qwen 3 Guard Stream 8B | - | 819 % | inferred family alias from qwen3-vl-8b-thinking (score=0.3371; benches=50) | Ja | - | |
| Qwen 3 VL 8B Thinking | - | 819 % | - | Ja | - | |
| Qwen 3 VL Embedding 8B | - | 819 % | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5232; benches=50) | Ja | - | |
| Qwen 3 VL Reranker 8B | - | 819 % | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5275; benches=50) | Ja | - | |
| Qwen 3 4B Instruct 2507 | - | 808 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48) | Ja | - | |
| Qwen 3 4B SafeRL | - | 808 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | Ja | - | |
| Qwen 3 4B Thinking 2507 | - | 808 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48) | Ja | - | |
| Qwen 3 Embedding 4B | - | 808 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | Ja | - | |
| Qwen 3 Guard Gen 4B | - | 808 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3400; benches=48) | Ja | - | |
| Qwen 3 Guard Stream 4B | - | 808 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3371; benches=48) | Ja | - | |
| Qwen 3 Reranker 4B | - | 808 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | Ja | - | |
| Qwen 3 VL 4B Thinking | - | 808 % | - | Ja | - | |
| Kimi K2.5 | 27. Jan. 2026 | 92,30 % | - | Ja | Quelle | |
| Qwen 3.5 122B A10B | 24. Feb. 2026 | 92,10 % | Raw score: 92.1 | Ja | Quelle | |
| Qwen 3.5 35B A3B | 24. Feb. 2026 | 91 % | Raw score: 91.0 | Ja | Quelle | |
| Qwen 3.5 27B | 24. Feb. 2026 | 89,40 % | Raw score: 89.4 | Ja | Quelle |
