Perception on HallusionBench
59.5ScoreAVAR-Thinker
Evaluation results
| Method | Links | |
|---|---|---|
| AVAR-ThinkerModel Category=Our model2026.03 | 59.5 | |
| Claude-3.7-SonnetModel Category=Closed-Source2026.03 | 58.3 | |
| GPT-4oModel Category=Closed-Source2026.03 | 56.2 | |
| Vision-SR1Model Category=Multimodal Reasoning Models2026.03 | 54.3 | |
| Mulberry-7BModel Category=Multimodal Reasoning Models2026.03 | 54.1 | |
| OpenVLThinkerModel Category=Multimodal Reasoning Models2026.03 | 53 | |
| ThinkLite-VLModel Category=Multimodal Reasoning Models2026.03 | 52.3 | |
| Vision-R1Model Category=Multimodal Reasoning Models2026.03 | 51.9 | |
| InternVL2.5-8BModel Category=Open-Source General Models2026.03 | 51.1 | |
| VLAA-Thinker-7BModel Category=Multimodal Reasoning Models2026.03 | 50.9 | |
| Qwen2.5-VL-7BModel Category=Open-Source General Models2026.03 | 50.7 | |
| MM-Eureka-7BModel Category=Multimodal Reasoning Models2026.03 | 50.7 | |
| LLaVA-OneVision-7BModel Category=Open-Source General Models2026.03 | 47.5 | |
| R1-OneVisionModel Category=Multimodal Reasoning Models2026.03 | 46 | |
| Llama-3.2-11B-Vision-InstructModel Category=Open-Source General Models2026.03 | 40.3 |