LVBench
Resultados de evaluaciones comparativas de IA y rendimiento de modelos
Tipo: percentageLong Context
Resultados registrados
41
Puntuación media
58.40%
Rango de puntuaciones
45.30% - 91.70%
Modelo líder
91.70% - Gemini 4 Argon
Puntuaciones a lo largo del tiempo
Puntuaciones individuales de la evaluación a lo largo del tiempo.
Resultados de modelos
| Organización | Modelos | Fecha del resultado | Mejor puntuación | Información | Autodeclarado | Fuente |
|---|---|---|---|---|---|---|
| Gemini 4 Argon | 13 oct 2026 | 91,70 % | Google-reported launch evaluation; source chart: https://storage.googleapis.com/gweb-uniblog-publish-prod/original_images/gemini-4-argon_table_blog.gif | Sí | Fuente | |
| Seed 2.0 Pro | 14 feb 2026 | 76,40 % | Seed2 official benchmark table | LVBench | Sí | Fuente | |
| Kimi K2.5 | 27 ene 2026 | 75,90 % | - | Sí | Fuente | |
| Qwen 3.5 122B A10B | 24 feb 2026 | 74,40 % | - | Sí | Fuente | |
| Qwen 3.5 27B | 24 feb 2026 | 73,60 % | - | Sí | Fuente | |
| Qwen 3.5 Flash | 23 feb 2026 | 73,60 % | inferred family alias from qwen3.5-27b (score=0.4147; benches=81) | Sí | Fuente | |
| Seed 2.0 Lite | 14 feb 2026 | 73 % | Seed2 official benchmark table | LVBench | Sí | Fuente | |
| Qwen 3.5 35B A3B | 24 feb 2026 | 71,40 % | - | Sí | Fuente | |
| Qwen 3 VL 235B A22B Instruct | - | 67,70 % | - | Sí | - | |
| Seed 2.0 Mini | 14 feb 2026 | 66,60 % | Seed2 official benchmark table | LVBench | Sí | Fuente | |
| Qwen 3 VL 32B Instruct | - | 63,80 % | - | Sí | - | |
| Qwen 3 VL 235B A22B Thinking | - | 63,60 % | - | Sí | - | |
| Qwen 3 VL 32B Thinking | - | 62,60 % | - | Sí | - | |
| Qwen 3 VL 30B A3B Instruct | - | 62,50 % | - | Sí | - | |
| Qwen 3 VL 30B A3B Thinking | - | 59,20 % | - | Sí | - | |
| Qwen 3 VL 8B Instruct | - | 58 % | - | Sí | - | |
| Qwen 3 VL 4B Instruct | - | 56,20 % | - | Sí | - | |
| Qwen 3 8B | - | 55,80 % | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.4600; benches=50) | Sí | - | |
| Qwen 3 Guard Stream 8B | - | 55,80 % | inferred family alias from qwen3-vl-8b-thinking (score=0.3371; benches=50) | Sí | - | |
| Qwen 3 VL 8B Thinking | - | 55,80 % | - | Sí | - | |
| Qwen 3 VL Embedding 8B | - | 55,80 % | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5232; benches=50) | Sí | - | |
| Qwen 3 VL Reranker 8B | - | 55,80 % | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5275; benches=50) | Sí | - | |
| Qwen 3 4B Instruct 2507 | - | 53,50 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48) | Sí | - | |
| Qwen 3 4B SafeRL | - | 53,50 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | Sí | - | |
| Qwen 3 4B Thinking 2507 | - | 53,50 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48) | Sí | - |
