Multimodal Reasoning on MM-IQ
27.3AccuracyOurs [with DPS and annealing]
Evaluation Results
| Method | Links | |
|---|---|---|
| Ours [with DPS and annealing]Model Category=Reasoning MLLMs, Training Strategy=Two-stage RL2026.01 | 27.3 | |
| GPT-4oModel Category=Closed-Source MLLMs2026.01 | 26.87 | |
| Gemini-1.5-ProModel Category=Closed-Source MLLMs2026.01 | 26.86 | |
| VLAA-Thinker 7BModel Category=Reasoning MLLMs2026.01 | 26.3 | |
| Ours [with DPS]Model Category=Reasoning MLLMs, Training Strategy=DPS2026.01 | 26.3 | |
| Qwen2.5VL 7BModel Category=Open-Source General MLLMs2026.01 | 26.1 | |
| MixedR1 7BModel Category=Reasoning MLLMs2026.01 | 25.9 | |
| OursModel Category=Reasoning MLLMs, Training Strategy=DAPO2026.01 | 25.6 | |
| R1-Onevision 7BModel Category=Reasoning MLLMs2026.01 | 25.1 | |
| VisonR1 7BModel Category=Reasoning MLLMs2026.01 | 24.3 |