Visual Reasoning on MME-RW Chinese
77.7AccuracyS1-VL-32B-RL
Evaluation Results
| Method | Links | |
|---|---|---|
| S1-VL-32B-RLCategory=Thinking-with-Images Specialist Models, Parameters=32B, Training Stage=RL2026.04 | 77.7 | |
| S1-VL-32B-SFTCategory=Thinking-with-Images Specialist Models, Parameters=32B, Training Stage=SFT2026.04 | 72 | |
| Skywork-R1V4-30BCategory=Thinking-with-Images Specialist Models, Parameters=30B2026.04 | 70.8 | |
| Gemini 2.5 ProCategory=Proprietary Models2026.04 | 69.3 | |
| Qwen3-VL-235B-A22B-ThinkingCategory=Open-Source Models, Parameters=235B-A22B2026.04 | 68.8 | |
| Thyme-VL (7B)Category=Thinking-with-Images Specialist Models, Parameters=7B2026.04 | 64.6 | |
| GPT-5Category=Proprietary Models2026.04 | 63.97 | |
| Intern-S1 (235B+6B)Category=Open-Source Models, Parameters=235B+6B2026.04 | 62.98 | |
| Qwen3-VL-32B-ThinkingCategory=Open-Source Models, Parameters=32B2026.04 | 61.21 | |
| Gemini 2.5 FlashCategory=Proprietary Models2026.04 | 61.2 | |
| Qwen2.5-VL-7BCategory=Open-Source Models, Parameters=7B2026.04 | 60.8 | |
| Qwen2.5-VL-32BCategory=Open-Source Models, Parameters=32B2026.04 | 60.5 | |
| InternVL3-8BCategory=Open-Source Models, Parameters=8B2026.04 | 60.5 | |
| Intern-S1-mini (8B)Category=Open-Source Models, Parameters=8B2026.04 | 54.67 |