ChartQA
Resultados de benchmarks de IA e desempenho dos modelos
Tipo: percentage
Resultados registrados
41
Pontuação média
85.69%
Faixa de pontuação
76.10% - 90%
Modelo líder
90% - Llama 4 Maverick
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 |
|---|---|---|---|---|---|---|
| Llama 4 Maverick | 05 de abr. de 2025 | 90% | - | Sim | Fonte | |
| Qwen 2.5 Math 72B | - | 89,50% | inferred high-confidence family alias from qwen2.5-vl-72b (score=0.4700; benches=30) | Sim | Fonte | |
| Qwen 2.5 Math PRM 72B | - | 89,50% | inferred family alias from qwen2.5-vl-72b (score=0.4050; benches=30) | Sim | Fonte | |
| Qwen 2.5 Math RM 72B | - | 89,50% | inferred family alias from qwen2.5-vl-72b (score=0.4092; benches=30) | Sim | Fonte | |
| Qwen 2.5 VL 72B Instruct | 26 de jan. de 2025 | 89,50% | - | Sim | Fonte | |
| Llama 4 Scout | 05 de abr. de 2025 | 88,80% | - | Sim | Fonte | |
| Qwen 2 VL 2B | - | 88,30% | inferred family alias from qwen2-vl-72b (score=0.4083; benches=15) | Sim | Fonte | |
| Qwen 2 VL 72B | - | 88,30% | - | Sim | Fonte | |
| Pixtral Large | 18 de nov. de 2024 | 88,10% | - | Sim | Fonte | |
| Mistral Small 3.2 | 20 de jun. de 2025 | 87,40% | - | Sim | Fonte | |
| Qwen 2.5 0.5B | - | 87,30% | inferred family alias from qwen2.5-vl-7b (score=0.3131; benches=32) | Sim | Fonte | |
| Qwen 2.5 1.5B | - | 87,30% | inferred family alias from qwen2.5-vl-7b (score=0.3131; benches=32) | Sim | Fonte | |
| Qwen 2.5 3B | - | 87,30% | inferred family alias from qwen2.5-vl-7b (score=0.3531; benches=32) | Sim | Fonte | |
| Qwen 2.5 VL 7B Instruct | - | 87,30% | - | Sim | Fonte | |
| DeepSeek VL2 | 13 de dez. de 2024 | 86% | - | Sim | Fonte | |
| GPT 4o (2024-08-06) | 06 de ago. de 2024 | 85,70% | - | Sim | Fonte | |
| GPT 4o Audio Preview (2025-06-03) | 03 de jun. de 2025 | 85,70% | inferred modality/version alias from gpt-4o-2024-08-06 | Sim | Fonte | |
| GPT 4o Audio Preview (2024-10-01) | 01 de out. de 2024 | 85,70% | inferred modality/version alias from gpt-4o-2024-08-06 | Sim | Fonte | |
| GPT 4o Audio Preview (2024-12-17) | 17 de dez. de 2024 | 85,70% | inferred modality/version alias from gpt-4o-2024-08-06 | Sim | Fonte | |
| GPT 4o Realtime Preview (2025-06-03) | 03 de jun. de 2025 | 85,70% | inferred modality/version alias from gpt-4o-2024-08-06 | Sim | Fonte | |
| GPT 4o Realtime Preview (2024-10-01) | 01 de out. de 2024 | 85,70% | inferred modality/version alias from gpt-4o-2024-08-06 | Sim | Fonte | |
| GPT 4o Search Preview | 11 de mar. de 2025 | 85,70% | inferred modality/version alias from gpt-4o-2024-08-06 | Sim | Fonte | |
| GPT 4o Transcribe | 20 de mar. de 2025 | 85,70% | inferred modality/version alias from gpt-4o-2024-08-06 | Sim | Fonte | |
| GPT 4o Transcribe Diarize | 15 de out. de 2025 | 85,70% | inferred modality/version alias from gpt-4o-2024-08-06 | Sim | Fonte | |
| Llama 3.2 90B Vision Instruct | - | 85,50% | inferred high-confidence family alias from llama-3.2-90b-instruct (score=0.5873; benches=13) | Sim | Fonte |
