Count Reasoning on CountQA (test)
25.03EMGPT-4o
Evaluation results
| Method | Links | |
|---|---|---|
| GPT-4oSupervision=Zero-shot/MLLM (Z)2026.06 | 25.03 | |
| ABACUS-3BSupervision=Zero-shot/MLLM (Z)2026.06 | 15.3 | |
| UniLIP-3BSupervision=Zero-shot/MLLM (Z)2026.06 | 9.23 | |
| WS-COC-7BSupervision=Image-level (I)2026.06 | 8.44 | |
| Show-oSupervision=Zero-shot/MLLM (Z)2026.06 | 7.85 | |
| Janus Pro 7BSupervision=Zero-shot/MLLM (Z)2026.06 | 6.98 |