Visual Question Answering on WorldSense sampled examples 1.0
60AccuracyGemini-3-Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-3-Pro2026.02 | 60 | |
| Gemini-2.5-Flash2026.02 | 58 | |
| Qwen3-Omni-Instruct2026.02 | 56 | |
| Qwen3-Omni-Thinking2026.02 | 56 |
Loading the SOTA2 catalog…