STEM & Reasoning on VLMAreBlind
91.38AccuracyERNIE 5.0
Evaluation Results
| Method | Links | |
|---|---|---|
| ERNIE 5.02026.02 | 91.38 | |
| Gemini 3-Pro2026.02 | 80.83 | |
| Gemini 2.5-Pro2026.02 | 76.54 | |
| Qwen3-VLmode=Thinking2026.02 | 75.13 | |
| GPT-5tier=High2026.02 | 69.6 |
| Method | Links | |
|---|---|---|
| ERNIE 5.02026.02 | 91.38 | |
| Gemini 3-Pro2026.02 | 80.83 | |
| Gemini 2.5-Pro2026.02 | 76.54 | |
| Qwen3-VLmode=Thinking2026.02 | 75.13 | |
| GPT-5tier=High2026.02 | 69.6 |