← All lab files

Anthropic research file

#1 on the current provider board.

Claude Fable 5 scores 1507.5 according to LMArena's text style-control snapshot published July 16, 2026.

LMArena source rank#1
LMArena rating1507.5
Reported interval1500.2–1514.7
Battles8,817

Model records from the Epoch AI catalog

Anthropic 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. Claude Fable 5

    Language, MultimodalAPI accessClosed weightsRead profile →

  2. Claude Mythos 5

    Language, MultimodalUnreleasedClosed weightsRead profile →

  3. Claude Opus 4.8

    LanguageAPI accessClosed weightsOpen record →

  4. Claude Opus 4.7

    LanguageAPI accessClosed weightsRead profile →

  5. Claude Opus 4.5

    Language, Multimodal, VisionAPI accessClosed weightsRead profile →

  6. Claude Haiku 4.5

    LanguageAPI accessClosed weightsRead profile →

  7. Claude Sonnet 4.5

    Language, Vision, MultimodalAPI accessClosed weightsOpen record →

  8. Claude Opus 4.1

    Language, Multimodal, VisionAPI accessClosed weightsOpen record →

  9. Claude Opus 4

    Language, Multimodal, VisionAPI accessClosed weightsOpen record →

  10. Claude Sonnet 4

    Language, Multimodal, VisionAPI accessClosed weightsOpen record →

  11. Claude 3.7 Sonnet

    Language, Vision, MultimodalAPI accessClosed weightsOpen record →

  12. Claude 3.5 Sonnet

    Multimodal, Language, VisionAPI accessClosed weightsOpen record →

Show all 17 catalog models

  1. Claude 3 Opus

    Multimodal, Language, VisionAPI accessClosed weightsOpen record →

  2. Claude 3 Sonnet

    Multimodal, Language, VisionAPI accessClosed weightsOpen record →

  3. Claude 2.1

    LanguageAPI accessClosed weightsOpen record →

  4. Claude 2

    LanguageAPI accessClosed weightsOpen record →

  5. Claude

    LanguageAPI accessClosed weightsOpen record →

Filter every reviewed record in the model explorer →

Historical momentum · legacy metric only

+191.9 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 sample1224.7claude-v1
Legacy peak1416.62025-08-29 · claude-opus-4-1-20250805-thinking-16k
Last sample1416.6claude-opus-4-1-20250805-thinking-16k
Show all 11 legacy observations
  1. claude-v11224.7
  2. claude-v11200.7
  3. claude-11203.7
  4. claude-2.11085.4
  5. claude-3-sonnet-202402291130.3
  6. claude-3-opus-202402291248.4
  7. claude-3-5-sonnet-202406201270.1
  8. claude-3-5-sonnet-202410221282.6
  9. claude-3-5-sonnet-202410221283.2
  10. claude-3-7-sonnet-20250219-thinking-32k1296.5
  11. claude-opus-4-1-20250805-thinking-16k1416.6

Release record

Latest matched notable models.

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

  1. Claude Fable 5
  2. Claude Mythos 5
  3. Claude Opus 4.7
  4. Claude Opus 4.5
  5. Claude Haiku 4.5

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