Mathematical Reasoning on PyraMathBench multimodal (test)
73VRPGPT-4o
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4o2026.06 | 73 | |
| GPT-4o mini2026.06 | 68.3 | |
| LLaVASize=13B2026.06 | 25.5 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| GPT-4o2026.06 | 73 | |
| GPT-4o mini2026.06 | 68.3 | |
| LLaVASize=13B2026.06 | 25.5 |