RealWorldQA
Ergebnisse von KI-Benchmarks und Modellleistung
Typ: percentageSpatial Reasoning
Erfasste Ergebnisse
43
Durchschnittspunktzahl
75.26%
Punktzahlbereich
64.20% - 86%
Führendes Modell
86% - Seed 2.0 Pro
Punktzahlen im Zeitverlauf
Einzelne Benchmark-Punktzahlen nach Datum.
Modellergebnisse
| Organisation | Modelle | Gemeldet am | Höchste Punktzahl | Info | Selbst gemeldet | Quelle |
|---|---|---|---|---|---|---|
| Seed 2.0 Pro | 14. Feb. 2026 | 86 % | Seed2 official benchmark table | RealWorldQA | Ja | Quelle | |
| Qwen 3.8 27B | 14. Aug. 2026 | 85,90 % | - | Ja | Quelle | |
| Qwen 3.6 Plus | 01. Apr. 2026 | 85,40 % | - | Ja | Quelle | |
| Qwen 3.5 122B A10B | 24. Feb. 2026 | 85,10 % | - | Ja | Quelle | |
| Qwen 3.5 35B A3B | 24. Feb. 2026 | 84,10 % | - | Ja | Quelle | |
| Qwen 3.5 27B | 24. Feb. 2026 | 83,70 % | - | Ja | Quelle | |
| Qwen 3.5 Flash | 23. Feb. 2026 | 83,70 % | inferred family alias from qwen3.5-27b (score=0.4147; benches=81) | Ja | Quelle | |
| Seed 2.0 Lite | 14. Feb. 2026 | 81,70 % | Seed2 official benchmark table | RealWorldQA | Ja | Quelle | |
| Seed 2.0 Mini | 14. Feb. 2026 | 81,60 % | Seed2 official benchmark table | RealWorldQA | Ja | Quelle | |
| Qwen 3 VL 235B A22B Thinking | - | 81,30 % | - | Ja | - | |
| Qwen 3 VL 235B A22B Instruct | - | 79,30 % | - | Ja | - | |
| Qwen 3 VL 32B Instruct | - | 79 % | - | Ja | - | |
| Qwen 3 VL 32B Thinking | - | 78,40 % | - | Ja | - | |
| Qwen 2 VL 2B | - | 77,80 % | inferred family alias from qwen2-vl-72b (score=0.4083; benches=15) | Ja | Quelle | |
| Qwen 2 VL 72B | - | 77,80 % | - | Ja | Quelle | |
| Qwen 3 VL 30B A3B Thinking | - | 77,40 % | - | Ja | - | |
| Qwen 3 VL 30B A3B Instruct | - | 73,70 % | - | Ja | - | |
| Qwen 3 8B | - | 73,50 % | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.4600; benches=50) | Ja | - | |
| Qwen 3 Guard Stream 8B | - | 73,50 % | inferred family alias from qwen3-vl-8b-thinking (score=0.3371; benches=50) | Ja | - | |
| Qwen 3 VL 8B Thinking | - | 73,50 % | - | Ja | - | |
| Qwen 3 VL Embedding 8B | - | 73,50 % | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5232; benches=50) | Ja | - | |
| Qwen 3 VL Reranker 8B | - | 73,50 % | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5275; benches=50) | Ja | - | |
| Qwen 3 4B Instruct 2507 | - | 73,20 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48) | Ja | - | |
| Qwen 3 4B SafeRL | - | 73,20 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | Ja | - | |
| Qwen 3 4B Thinking 2507 | - | 73,20 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48) | Ja | - |
