General Visual Understanding on ScienceQA
89.92AccuracyIREASONER
Evaluation results
| Method | Links | |
|---|---|---|
| IREASONERReward Type=Continuous, Aggregation=Step-level Majority2026.01 | 89.92 | |
| EvoLMM2026.01 | 89.5 | |
| Qwen2.5-VL-7B w/ Discrete Reward + Step-level MajorityReward Type=Discrete, Aggregation=Step-level Majority2026.01 | 88.92 | |
| Vision-Zeroexternal supervision=true2026.01 | 88.5 | |
| Qwen2.5-VL-7B (Baseline)Backbone=Qwen2.5-VL-7B2026.01 | 88.3 | |
| Qwen2.5-VL-7B w/ Discrete RewardReward Type=Discrete2026.01 | 87.98 |