| Unlocking Dense Metric Depth Estimation in VLMs | ✓ Link | 98.2 | DepthVLM-8B | 2026-05-15 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 97.8 | Qwen3.5-27B | 2026-02-16 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 97.8 | Qwen3.5-35B-A3B | 2026-02-16 |
| Qwen3.6 | ✓ Link | 97.8 | Qwen3.6-27B | 2026-04-21 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 97.2 | Qwen3.5-397B-A17B | 2026-02-16 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 97.2 | Qwen3.5-9B | 2026-02-16 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 97.0 | Qwen3.5-122B-A10B | 2026-02-16 |
| Qwen3.6 | ✓ Link | 96.1 | Qwen3.6-35B-A3B | 2026-04-21 |
| Evidence-RL: Towards Evidence-intensive Visual Reasoning | | 95.92 | Evidence-RL (Qwen3-VL-8B) | 2026-08-08 |
| Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding | ✓ Link | 95.1 | Molmo2-O-7B | 2026-01-15 |
| Qwen3.5-Omni Technical Report | | 95.1 | Qwen3.5-Omni-Plus | 2026-04-21 |
| SAM 3: Segment Anything with Concepts | ✓ Link | 93.8 | SAM 3 (zero-shot) | 2025-11-20 |
| Qwen3-VL Technical Report | ✓ Link | 93.7 | Qwen3-VL-235B-A22B-Thinking | 2025-11-26 |
| Qwen2.5-VL Technical Report | ✓ Link | 93.6 | Qwen2.5-VL-72B | 2025-02-19 |
| Qwen3-Omni Technical Report | ✓ Link | 92.5 | Qwen3-Omni-Flash-Thinking | 2025-09-22 |
| LongCat-Flash-Omni Technical Report | ✓ Link | 92.4 | LongCat-Flash-Omni | 2025-10-31 |
| Metric-Bench: Exploring In-context Spatial Metric Reasoning in VLMs for Indoor Scenes | | 92.0 | MetricReasoner | 2026-09-08 |
| Cosmos 3: Omnimodal World Models for Physical AI | ✓ Link | 89.1 | Cosmos3-Super | 2026-06-01 |
| ERNIE 4.5 Technical Report | ✓ Link | 89.0 | ERNIE-4.5-VL-424B-A47B | 2025-06-30 |
| LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence | ✓ Link | 89.0 | LLaVA-OneVision-2-8B | 2026-05-25 |
| STEP3-VL-10B Technical Report | ✓ Link | 88.8 | Step3-VL-10B (PaCoRe) | 2026-01-14 |
| Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision | ✓ Link | 88.6 | Youtu-VL (4B) | 2026-01-27 |
| LLaDA-UI: Bringing Block-wise Diffusion to Vision-Language GUI Agents | ✓ Link | 86.2 | LLaDA-UI (pre-training) | 2026-09-09 |
| LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model | ✓ Link | 86.0 | LLaDA2.0-Uni (16B) | 2026-04-22 |
| MOSS-VL Technical Report | ✓ Link | 85.9 | MOSS-VL-Instruct-0708 | 2026-08-15 |
| LongCat-Next: Lexicalizing Modalities as Discrete Tokens | ✓ Link | 82.1 | LongCat-Next (A3B, 68.5B) | 2026-03-29 |
| LFM2.5-VL-450M: Structured Visual Intelligence, Edge to Cloud | | 73.31 | LFM2.5-VL-450M | 2026-04-08 |