all the models — AI benchmark observatory

Updates

Recently added or refreshed models in the catalog.

  1. 01
    GPT-6 Sol
    OpenAI · closed
    2026-09-22
  2. 02
    GPT-6 Luna
    OpenAI · closed
    2026-09-22
  3. 03
    Claude Opus 5.5
    Anthropic · closed
    2026-09-22
  4. 04
    MiMo-V2.6-Pro
    Xiaomi · open
    2026-09-22
  5. 05
    MiMo-V2.6-Flash
    Xiaomi · open
    2026-09-22
  6. 06
    Grok 4.7
    xAI · closed
    2026-09-21
  7. 07
    Atria Dawn Preview
    Shanghai AI Laboratory · open
    2026-09-11
  8. 08
    Kimi K2.8 Preview
    Moonshot AI · closed
    2026-09-11
  9. 09
    DeepSeek-V4.1-Flash
    DeepSeek · open
    2026-09-10
  10. 10
    Qwen3 Max Thinking
    Alibaba Cloud / Qwen Team · closed
    2026-02-13
  11. 11
    Llama Guard 4 12B
    Meta · open
    2025-04-28
  12. 12
    L3.1 70B Euryale v2.2
    Sao10K · closed
    2024-09-12
  13. 13
    Hermes 3 405B
    Nous Research · open
    2024-10-09
  14. 14
    Ling 3.0 Flash Fin
    InclusionAI · closed
    2026-09-03
  15. 15
    Inkling
    Thinking Machines Lab · open
    2026-07-21
  16. 16
    Step 3.7 Flash
    StepFun · open
    2026-06-10
  17. 17
    L3 8B Lunaris v1
    Sao10K · closed
    2025-04-09
  18. 18
    Qwen3 14B
    Alibaba Cloud / Qwen Team · open
    2025-04-28
  19. 2026-06-01
  20. 20
    Ling 3.0 Flash
    InclusionAI · closed
    2026-08-04
  21. 21
    MythoMax L2 13B
    Gryphe · closed
    2023-10-04
  22. 22
    Seed 2.0 Mini
    ByteDance · closed
    2026-02-17
  23. 23
    Seed 2.0 Code
    ByteDance · closed
    2026-04-29
  24. 24
    Seed 1.8
    ByteDance · closed
    2026-02-17
  25. 25
    Claude Mythos 5.1
    Anthropic · closed
    2026-09-01
  26. 26
    GPT-6 Astra
    OpenAI · closed
    2026-09-04
  27. 27
    Muse Spark 1.3
    Meta · closed
    2026-09-02
  28. 28
    Gemini 3.8 Flash Cyber
    Google · closed
    2026-09-02
  29. 29
    Gemini 3.8 Flash
    Google · closed
    2026-09-02
  30. 30
    Claude Fable 5.1
    Anthropic · closed
    2026-09-01
  31. 31
    Hy4 preview
    Tencent · open
    2026-08-28
  32. 32
    Qwen3.8 Flash
    Alibaba Cloud / Qwen Team · closed
    2026-08-26
  33. 33
    Parse
    Cohere · closed
    2026-08-27
  34. 34
    2026-08-25
  35. 35
    2026-08-25
  36. 36
    2026-08-25
  37. 37
    Qwen3.8-Flash-Next
    Alibaba Cloud / Qwen Team · open
    2026-08-26
  38. 38
    GLM-5.3-Flash
    Zhipu AI · open
    2026-08-26
  39. 39
    EXAONE 4.5 33B
    LG AI Research · closed
    2026-04-09
  40. 40
    2026-08-21