OpenGPTEvidence-based model decisions
Search⌘K
Public ranking sources

LMArena AI model ranking data

OpenGPT preserves 385 published LMArena records in their original source scope. It does not rerun or blend this ranking with another benchmark.

Published records
385
Ranking views
User preference
Source data date
Retrieved

Evidence scope

Text Style Control · latest · 2026-08-06. All 385 published model entries in the official latest overall text style control snapshot; source ranks are preserved. Text · Style control · Overall.

How OpenGPT handles this evidence

OpenGPT stores the publisher's labels, positions, configurations, dates, and values within the same published scope. It does not convert missing values to zero or merge this source into a cross-source score.

Comparison boundaries

  • Ranks and values are comparable only inside the named source release and ranking scope.
  • A source-listed configuration is linked to an official model ID only when identity evidence has been reviewed.
  • Published rankings are screening signals; production choice still requires testing the exact version on real work.

Text Style Control

Showing 6 representative rows from 385 published records. Follow a row to inspect its exact source identity and mapping evidence.

  1. claude-fable-5Anthropic · User preference#11507Text · Style control · Overall
  2. claude-opus-4-6-thinkingAnthropic · User preference#21505Text · Style control · Overall
  3. claude-opus-4-7-thinkingAnthropic · User preference#31502Text · Style control · Overall
  4. muse-spark-1.2 (xHigh)Meta · User preference#41498Text · Style control · Overall
  5. claude-opus-4-6Anthropic · User preference#51497Text · Style control · Overall
  6. qwen3.8-maxAlibaba · User preference#61497Text · Style control · Overall