Trending papers, with their scores.

Meta shut down Papers with Code in July 2025 and the trending feed went with it. This is what we’re building in its place — recent ML papers, sorted by publication date, with at least one reproduced benchmark result on each. If a paper isn’t scored, it doesn’t appear.

Each row links to a paper page with every reproduced score, related models, and the dataset(s) it introduced.

50 papers, newest first.

1. #01· 2026-05-18

   HRM-Text: Efficient Pretraining Beyond Scaling

2. #02· 2026-05-18

   Spectral Progressive Diffusion for Efficient Image and Video Generation

3. #03· 2026-05-13

   A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone

4. #04· 2026-05-13

   Asymmetric Flow Models

5. #05· 2026-05-13

   Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling

6. #06· 2026-05-12

   SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture

7. #07· 2026-05-11

   Infinity-Parser2-Pro

8. #08· 2026-05-08

   ZAYA1-VL-8B Technical Report

9. #09· 2026-05-08

   jina-embeddings-v5-omni: Text-Geometry-Preserving Multimodal Embeddings via Frozen-Tower Composition

10. #10· 2026-05-06

    ZAYA1-8B Technical Report

11. #11· 2026-05-04· Agentic AI

    AcademiClaw: When Students Set Challenges for AI Agents

    Junjie Yu, Pengrui Lu, Weiye Si, Hongliang Lu et al.
12. #12· 2026-05-04

    MolmoAct2: Action Reasoning Models for Real-world Deployment

13. #13· 2026-04-30

    MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction

14. #14· 2026-04-29

    Ling-2.6-1T: A Trillion-Parameter Comprehensive Flagship Model for Complex Tasks

15. #15· 2026-04-29

    GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents

16. #16· 2026-04-27

    MiMo-V2.5-Pro

17. #17· 2026-04-24

    DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

18. #18· 2026-04-21

    Qwen3.6

19. #19· 2026-04-20

    Kimi K2.6

20. #20· 2026-04-17

    Qwen3.5-Omni Technical Report

21. #21· 2026-04-02

    Gemma 4: Byte for byte, the most capable open models

22. #22· 2026-04-01

    Holo3: Foundational Models for Navigation and Computer Use Agents

23. #23· 2026-03-28

    Falcon Perception

24. #24· 2026-03-26

    Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale

25. #25· 2026-03-24

    Cohere Transcribe: state-of-the-art speech recognition

26. #26· 2026-03-19

    F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World

27. #27· 2026-03-16

    Chandra OCR 2

28. #28· 2026-03-13

    Multimodal OCR: Parse Anything from Documents

29. #29· 2026-03-11

    Qianfan-OCR: A Unified End-to-End Model for Document Intelligence

30. #30· 2026-03-11

    GLM-OCR Technical Report

31. #31· 2026-03-02

    FireRed-OCR Technical Report

32. #32· 2026-02-28

    Qwen3-Coder-Next Technical Report

33. #33· 2026-02-19

    Arcee Trinity Large Technical Report

34. #34· 2026-02-19

    Niagara Batch English SSM

35. #35· 2026-02-17

    GLM-5: from Vibe Coding to Agentic Engineering

36. #36· 2026-02-17

    jina-embeddings-v5-text: Task-Targeted Embedding Distillation

37. #37· 2026-02-16

    Qwen3.5: Towards Native Multimodal Agents

38. #38· 2026-02-12

    MiniMax-M2.5

39. #39· 2026-02-11

    Voxtral Realtime

40. #40· 2026-02-11

    Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters

41. #41· 2026-02-05

    Bagging-Based Model Merging for Robust General Text Embeddings

42. #42· 2026-02-03

    Holo2: Foundational Models for Navigation and Computer Use Agents

43. #43· 2026-02-02

    Kimi K2.5: Visual Agentic Intelligence

44. #44· 2026-01-29

    Qwen3-ASR Technical Report

45. #45· 2026-01-28

    DeepSeek-OCR 2: Visual Causal Flow

46. #46· 2026-01-26

    VIBEVOICE-ASR Technical Report

47. #47· 2026-01-20

    LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR

48. #48· 2026-01-14

    Ultralytics YOLO26

49. #49· 2026-01-12

    okestro-ai-lab/SYMPHONY-ASR

50. #50· 2026-01-06

    Moonshine Streaming

Three places to go from here.