Exact model configurations ranked by the official objective LiveBench release. This is a single-family capability orientation, not an absolute composite.
RANK.AI DATA / LATEST PUBLICATION
Arena text preference
378 models ranked by arena text style controlled rating.
claude-fable-5 is out in front at 1,507.3 arena_score.
378 modelschecked Jul 21, 2026, 11:59 PM UTCdaily90 failed refresheshow we measure this →CSV / JSON
In front today
claude-fable-5
1,507.3 arena_scorearena text style controlled rating
- Ahead of second place
- 2.5
- Held by the top three
- 1%
- Middle of the board
- 1,347
Highest 1,507.3 arena_scoreMiddle 1,347
WHY THIS RANK / VERIFIED SNAPSHOT
alpaca-13b
Ranks official Arena model identifiers by the published style-controlled text overall rating.
partialPermalink to this snapshot ↗
Some explanation inputs are unavailable Missing: publicFrozenEvidence, comparablePriorRanking.
- Published rank
- #367
- Score
- 1,068.446
- Sample size
- 5,745
100% confidence · 36% component coverage · as of Jul 21, 2026, 11:59 PM UTC
SCORE CONSTRUCTION
5/14 evidencedComponent ledger
| Component | Value | Weight | Contribution | Evidence | Status |
|---|---|---|---|---|---|
| arena text rating lower bound | — | 0% | 0 | 1 | available |
| arena text rating upper bound | — | 0% | 0 | 1 | available |
| arena text rating variance | — | 0% | 0 | 1 | available |
| arena text style controlled rating | — | 100% | 1,068.446 | 1 | available |
| arena text vote count | — | 0% | 0 | 1 | available |
| datasetRevision | fb100fd1a48607efb93e28ba6610b641a7ac1bce | Unavailable | — | 0 | unavailableno_public_frozen_evidence |
| metrics | Structured | Unavailable | — | 0 | unavailableno_public_frozen_evidence |
| modelLicense | Non-commercial | Unavailable | — | 0 | unavailableno_public_frozen_evidence |
| organization | — | Unavailable | — | 0 | unavailableno_public_frozen_evidence |
| publishDate | 2026-07-21 | Unavailable | — | 0 | unavailableno_public_frozen_evidence |
| rankingDirection | descending | Unavailable | — | 0 | unavailableno_public_frozen_evidence |
| sourceModelId | alpaca-13b | Unavailable | — | 0 | unavailableno_public_frozen_evidence |
| styleControlled | 1 | Unavailable | — | 0 | unavailableno_public_frozen_evidence |
| upstreamRank | 367 | Unavailable | 367 | 0 | unavailableno_public_frozen_evidence |
WHY IT MOVED
No rank deltanew since prior snapshot
no_prior_published_snapshot
No component moved since the prior snapshot.
PRIMARY EVIDENCE
5 public recordsSource trail
Arena rating lower confidence boundarena text rating lower bound · observed Jul 21, 2026, 11:59 PM UTC1,056.998 arena_score100% confidence
- Source
- Arena official leaderboard dataset
- Grade
- A
- Freshness
- fresh
- Locator
{"filter":"category = overall","datasetCard":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/fb100fd1a48607efb93e28ba6610b641a7ac1bce/README.md","methodology":"https://github.com/lmarena/arena-rank","datasetSplit":"latest","datasetConfig":"text_style_control","datasetRevision":"fb100fd1a48607efb93e28ba6610b641a7ac1bce"}
Arena rating upper confidence boundarena text rating upper bound · observed Jul 21, 2026, 11:59 PM UTC1,079.895 arena_score100% confidence
- Source
- Arena official leaderboard dataset
- Grade
- A
- Freshness
- fresh
- Locator
{"filter":"category = overall","datasetCard":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/fb100fd1a48607efb93e28ba6610b641a7ac1bce/README.md","methodology":"https://github.com/lmarena/arena-rank","datasetSplit":"latest","datasetConfig":"text_style_control","datasetRevision":"fb100fd1a48607efb93e28ba6610b641a7ac1bce"}
Arena rating variancearena text rating variance · observed Jul 21, 2026, 11:59 PM UTC34.121 arena_score_squared100% confidence
- Source
- Arena official leaderboard dataset
- Grade
- A
- Freshness
- fresh
- Locator
{"filter":"category = overall","datasetCard":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/fb100fd1a48607efb93e28ba6610b641a7ac1bce/README.md","methodology":"https://github.com/lmarena/arena-rank","datasetSplit":"latest","datasetConfig":"text_style_control","datasetRevision":"fb100fd1a48607efb93e28ba6610b641a7ac1bce"}
Arena text style-controlled ratingarena text style controlled rating · observed Jul 21, 2026, 11:59 PM UTC1,068.446 arena_score100% confidence
- Source
- Arena official leaderboard dataset
- Grade
- A
- Freshness
- fresh
- Locator
{"filter":"category = overall","datasetCard":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/fb100fd1a48607efb93e28ba6610b641a7ac1bce/README.md","methodology":"https://github.com/lmarena/arena-rank","datasetSplit":"latest","datasetConfig":"text_style_control","datasetRevision":"fb100fd1a48607efb93e28ba6610b641a7ac1bce"}
Arena vote countarena text vote count · observed Jul 21, 2026, 11:59 PM UTC5,745 votes100% confidence
- Source
- Arena official leaderboard dataset
- Grade
- A
- Freshness
- fresh
- Locator
{"filter":"category = overall","datasetCard":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/fb100fd1a48607efb93e28ba6610b641a7ac1bce/README.md","methodology":"https://github.com/lmarena/arena-rank","datasetSplit":"latest","datasetConfig":"text_style_control","datasetRevision":"fb100fd1a48607efb93e28ba6610b641a7ac1bce"}
More in Model rank
Capability-first rankings across frontier and open models.
Exact model-plus-inference configurations ranked by UC Berkeley BFCL V4 overall accuracy, with tool-use breakdowns, cost, latency, and source evidence.
Hugging Face repository downloads and engagement for a fixed, reviewed model cohort.