LVBench
Resultados de benchmarks de IA e desempenho dos modelos
Tipo: percentageLong Context
Resultados registrados
41
Pontuação média
58.40%
Faixa de pontuação
45.30% - 91.70%
Modelo líder
91.70% - Gemini 4 Argon
Pontuações ao longo do tempo
Pontuações individuais do benchmark exibidas por data.
Resultados de modelos
| Organização | Modelos | Data informada | Maior pontuação | Informações | Declarado pelo provedor | Fonte |
|---|---|---|---|---|---|---|
| Gemini 4 Argon | 13 de out. de 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 | Sim | Fonte | |
| Seed 2.0 Pro | 14 de fev. de 2026 | 76,40% | Seed2 official benchmark table | LVBench | Sim | Fonte | |
| Kimi K2.5 | 27 de jan. de 2026 | 75,90% | - | Sim | Fonte | |
| Qwen 3.5 122B A10B | 24 de fev. de 2026 | 74,40% | - | Sim | Fonte | |
| Qwen 3.5 27B | 24 de fev. de 2026 | 73,60% | - | Sim | Fonte | |
| Qwen 3.5 Flash | 23 de fev. de 2026 | 73,60% | inferred family alias from qwen3.5-27b (score=0.4147; benches=81) | Sim | Fonte | |
| Seed 2.0 Lite | 14 de fev. de 2026 | 73% | Seed2 official benchmark table | LVBench | Sim | Fonte | |
| Qwen 3.5 35B A3B | 24 de fev. de 2026 | 71,40% | - | Sim | Fonte | |
| Qwen 3 VL 235B A22B Instruct | - | 67,70% | - | Sim | - | |
| Seed 2.0 Mini | 14 de fev. de 2026 | 66,60% | Seed2 official benchmark table | LVBench | Sim | Fonte | |
| Qwen 3 VL 32B Instruct | - | 63,80% | - | Sim | - | |
| Qwen 3 VL 235B A22B Thinking | - | 63,60% | - | Sim | - | |
| Qwen 3 VL 32B Thinking | - | 62,60% | - | Sim | - | |
| Qwen 3 VL 30B A3B Instruct | - | 62,50% | - | Sim | - | |
| Qwen 3 VL 30B A3B Thinking | - | 59,20% | - | Sim | - | |
| Qwen 3 VL 8B Instruct | - | 58% | - | Sim | - | |
| Qwen 3 VL 4B Instruct | - | 56,20% | - | Sim | - | |
| Qwen 3 8B | - | 55,80% | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.4600; benches=50) | Sim | - | |
| Qwen 3 Guard Stream 8B | - | 55,80% | inferred family alias from qwen3-vl-8b-thinking (score=0.3371; benches=50) | Sim | - | |
| Qwen 3 VL 8B Thinking | - | 55,80% | - | Sim | - | |
| Qwen 3 VL Embedding 8B | - | 55,80% | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5232; benches=50) | Sim | - | |
| Qwen 3 VL Reranker 8B | - | 55,80% | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5275; benches=50) | Sim | - | |
| Qwen 3 4B Instruct 2507 | - | 53,50% | inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48) | Sim | - | |
| Qwen 3 4B SafeRL | - | 53,50% | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | Sim | - | |
| Qwen 3 4B Thinking 2507 | - | 53,50% | inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48) | Sim | - |
