← All lab files

OpenAI research file

#3 on the current provider board.

GPT-5.6 Sol X-High scores 1486.3 according to LMArena's text style-control snapshot published July 16, 2026.

LMArena source rank#3
LMArena rating1486.3
Reported interval1476.8–1495.8
Battles4,113

Model records from the Epoch AI catalog

OpenAI models in the reviewed record.

Release date, domains, tasks, access, and weight availability come from the Epoch AI catalog. These fields describe models but do not rank them.

  1. GPT-5.5

    Multimodal, Language, VisionAPI accessClosed weightsRead profile →

  2. GPT-5.5 Pro

    Multimodal, Language, VisionAPI accessClosed weightsOpen record →

  3. GPT Image 2

    Image generationAPI accessClosed weightsRead profile →

  4. GPT-5.4

    Multimodal, Language, VisionAPI accessClosed weightsOpen record →

  5. GPT-5.4 Pro

    Multimodal, Language, VisionAPI accessClosed weightsOpen record →

  6. GPT-5.3 Codex

    LanguageAPI accessClosed weightsRead profile →

  7. GPT-5.2 Codex

    LanguageAPI accessClosed weightsOpen record →

  8. GPT-5.2

    Domains not documentedAPI accessClosed weightsOpen record →

  9. GPT-5.2 Pro

    Multimodal, Language, VisionAPI accessClosed weightsOpen record →

  10. GPT-5.1-Codex-Max

    LanguageAPI accessClosed weightsOpen record →

  11. GPT-5.1

    Multimodal, Language, VisionAPI accessClosed weightsOpen record →

  12. GPT-5.1 Instant

    Multimodal, Language, VisionAPI accessClosed weightsOpen record →

Show all 65 catalog models

  1. GPT-5.1-Codex

    LanguageAPI accessClosed weightsOpen record →

  2. GPT-5 Pro

    Multimodal, Language, VisionAPI accessClosed weightsOpen record →

  3. Sora 2.0

    VideoHosted access (no API)Closed weightsOpen record →

  4. GPT-5

    Multimodal, Language, VisionAPI accessClosed weightsOpen record →

  5. GPT-5 mini

    Multimodal, Language, VisionAPI accessClosed weightsOpen record →

  6. GPT-5 nano

    Multimodal, Language, VisionAPI accessClosed weightsOpen record →

  7. gpt-oss-120b

    LanguageOpen weights (unrestricted)Open weightsOpen record →

  8. gpt-oss-20b

    LanguageOpen weights (unrestricted)Open weightsOpen record →

  9. gpt-image-1

    Image generation, VisionAPI accessClosed weightsOpen record →

  10. GPT-4o (Mar 2025)

    Multimodal, Language, Audio, Speech, VisionAPI accessClosed weightsOpen record →

  11. o1-pro

    Language, Mathematics, MultimodalAPI accessClosed weightsOpen record →

  12. GPT-4.5

    Language, Vision, MultimodalAPI accessClosed weightsOpen record →

  13. o3-mini

    LanguageAPI accessClosed weightsOpen record →

  14. GPT-4o (Jan 2025)

    Multimodal, Language, Audio, Speech, VisionAPI accessClosed weightsOpen record →

  15. Computer-Using Agent (CUA)

    Vision, Language, MultimodalHosted access (no API)Closed weightsOpen record →

  16. o3

    Language, Vision, MultimodalAPI accessClosed weightsOpen record →

  17. Sora Turbo

    Video, VisionHosted access (no API)Closed weightsOpen record →

  18. o1

    Language, Mathematics, MultimodalAPI accessClosed weightsOpen record →

  19. GPT-4o (Nov 2024)

    Multimodal, Language, Audio, Speech, VisionAPI accessClosed weightsOpen record →

  20. o1-mini

    LanguageAPI accessClosed weightsOpen record →

  21. o1-preview

    Language, Mathematics, BiologyAPI accessClosed weightsOpen record →

  22. GPT-4o (Aug 2024)

    Multimodal, Language, Audio, Speech, VisionAPI accessClosed weightsOpen record →

  23. GPT-4o mini

    Language, Multimodal, VisionAPI accessClosed weightsOpen record →

  24. GPT-4o

    Multimodal, Language, Audio, Speech, VisionAPI accessClosed weightsOpen record →

  25. GPT-4 Turbo (Apr 2024)

    Multimodal, Vision, Language, Image generationAPI accessClosed weightsOpen record →

  26. Sora

    Video, VisionHosted access (no API)Closed weightsOpen record →

  27. GPT-4 Turbo (Nov 2023)

    Multimodal, Vision, Language, Image generationAPI accessClosed weightsOpen record →

  28. DALL·E 3

    Image generationAPI accessClosed weightsOpen record →

  29. GPT-3.5 Turbo Instruct

    LanguageAPI accessClosed weightsOpen record →

  30. GPT-4V

    Multimodal, Vision, LanguageAPI accessClosed weightsOpen record →

  31. GPT-3.5 Turbo

    LanguageAPI accessClosed weightsOpen record →

  32. GPT-4 (Jun 2023)

    Multimodal, Language, VisionAPI accessClosed weightsOpen record →

  33. GPT-4 (Mar 2023)

    Multimodal, Language, VisionAPI accessClosed weightsOpen record →

  34. Whisper

    SpeechOpen weights (unrestricted)Open weightsOpen record →

  35. DALL·E 2

    Image generationAPI accessClosed weightsOpen record →

  36. GPT-3.5 (davinci-002)

    LanguageAPI accessClosed weightsOpen record →

  37. Statement Curriculum Learning

    Language, MathematicsAPI accessClosed weightsOpen record →

  38. InstructGPT 1.3B

    LanguageAPI accessClosed weightsOpen record →

  39. InstructGPT 175B

    LanguageAPI accessClosed weightsOpen record →

  40. InstructGPT 6B

    LanguageAPI accessClosed weightsOpen record →

  41. Codex

    LanguageAPI accessClosed weightsOpen record →

  42. ADM

    Image generationOpen weights (non-commercial)Open weightsOpen record →

  43. CLIP (ResNet-50)

    Multimodal, Vision, Language, VideoOpen weights (unrestricted)Open weightsOpen record →

  44. CLIP (ViT L/14@336px)

    Multimodal, Vision, Language, VideoOpen weights (unrestricted)Open weightsOpen record →

  45. DALL-E

    Image generationAPI accessClosed weightsOpen record →

  46. GPT-3 175B (davinci)

    LanguageAPI accessClosed weightsOpen record →

  47. OpenAI Five

    GamesUnreleasedClosed weightsOpen record →

  48. OpenAI Five Rerun

    GamesUnreleasedClosed weightsOpen record →

  49. MuseNet

    AudioUnreleasedClosed weightsOpen record →

  50. GPT-2 (1.5B)

    LanguageOpen weights (unrestricted)Open weightsOpen record →

  51. GPT-1

    LanguageOpen weights (unrestricted)Open weightsOpen record →

  52. OpenAI TI7 DOTA 1v1

    GamesNot documented in sourceWeights unknownOpen record →

  53. GAN-Advancer

    VisionUnreleasedClosed weightsOpen record →

Filter every reviewed record in the model explorer →

Historical momentum · legacy metric only

+155.2 from first to last sampled observation.

This change is calculated only inside the selected legacy series, from May 8, 2023 to August 29, 2025. The archive crosses methodology changes and cannot be joined to, trended into, or compared numerically with the current snapshot.

First sample1274.2gpt-4
Legacy peak1429.42025-08-29 · chatgpt-4o-latest-20250326
Last sample1429.4chatgpt-4o-latest-20250326
Show all 11 legacy observations
  1. gpt-41274.2
  2. gpt-41184.9
  3. gpt-41149.6
  4. gpt-4-turbo1228.3
  5. gpt-4-0125-preview1211.4
  6. gpt-4o-2024-05-131286.7
  7. chatgpt-4o-latest1316.2
  8. chatgpt-4o-latest-202411201361.3
  9. chatgpt-4o-latest-202411201365.3
  10. o3-2025-04-161409.1
  11. chatgpt-4o-latest-202503261429.4

Release record

Latest matched notable models.

Epoch AI records provide dated context only. A release record does not imply a score change.

  1. GPT-5.5
  2. GPT-5.5 Pro
  3. GPT Image 2
  4. GPT-5.4
  5. GPT-5.4 Pro

Continue researching

Profiles, guides, and reports.

Evidence boundary

Three sources. Three distinct jobs.

Current frontier: LMArena leaderboard dataset, revision afed939e10281b660a4369206ca505b2bf5e0208, CC BY 4.0.

Historical context: LMArena historical Space artifacts, with one SHA-256 receipt per selected sample and no continuity to the current metric.

Catalog and releases: Epoch AI notable models. No corporate profile is added because our sources do not establish company-level facts beyond model authorship.

Read the full methodology