OpenGPTLMArena
The complete latest style-controlled overall ranking, based on users comparing two model answers side by side.
- Leaderboard publication date
- Sep 13, 2026
- Data retrieved
- Sep 19, 2026
- License
- CC BY 4.0
Independent model decisions
AI model rankings
Shortlist exact model versions from public evidence, compare them on one basis, then verify the choice on your own task.
- Rank 1claude-fable-5Anthropic1506
- Rank 2claude-opus-4-6-highAnthropic1505
- Rank 3claude-opus-4-7-highAnthropic1502
Published evaluation data2 external public sourcesLMArena · Edition data cutoff
OpenGPT organizes published third-party evaluation data; it did not rerun these tests. Use the rankings to shortlist models, then validate them on your own work.
Choose a ranking metric
Start with the decision you need to make. Each scenario opens the most relevant published ranking signal. The original source and scale remain visible.
Show every publisher record with its source model ID or source name, including aliases and run configurations. Source ranks are preserved; ties can still cause rank numbers to skip.
User preference score. LMArena’s complete latest style-controlled overall ranking. Every publisher record keeps its source model ID; a provider-documented model ID appears separately when available.
Compared with previous edition Jul 21, 2026. Same source and method. Rank movement is relative; it does not by itself prove a change in model quality.
Showing 10 of 402. User preference score.
- Rank 1
claude-fable-5
Anthropic- Votes cast
- 30,057
- License type
- Closed / proprietaryProprietary
User preference score1506Based on anonymous head-to-head comparisonsLikely score range1,500.9–1,510.4Review match evidence · View source
- Rank 2
claude-opus-4-6-high
Anthropic- Votes cast
- 71,993
- License type
- Closed / proprietaryProprietary
User preference score1505Based on anonymous head-to-head comparisonsLikely score range1,501.0–1,508.1View source
- Rank 3
claude-opus-4-7-high
Anthropic- Votes cast
- 60,002
- License type
- Closed / proprietaryProprietary
User preference score1502Based on anonymous head-to-head comparisonsLikely score range1,497.9–1,505.6View source
- Rank 4
- Votes cast
- 3,227
- License type
- Closed / proprietaryProprietary
User preference score1500Based on anonymous head-to-head comparisonsLikely score range1,489.1–1,510.1View source
- Rank 5
claude-fable-5.1-max
Anthropic- Votes cast
- 5,783
- License type
- Closed / proprietaryProprietary
User preference score1498Based on anonymous head-to-head comparisonsLikely score range1,490.3–1,506.6View source
- Rank 6
claude-opus-4-6
Anthropic- Votes cast
- 75,878
- License type
- Closed / proprietaryProprietary
User preference score1497Based on anonymous head-to-head comparisonsLikely score range1,493.9–1,500.8View source
- Rank 7
claude-opus-4-7
Anthropic- Votes cast
- 61,128
- License type
- Closed / proprietaryProprietary
User preference score1494Based on anonymous head-to-head comparisonsLikely score range1,490.6–1,498.3View source
- Rank 8
- Votes cast
- 4,723
- License type
- Closed / proprietaryProprietary
User preference score1493Based on anonymous head-to-head comparisonsLikely score range1,484.3–1,502.0View source
- Rank 9
gemini-3.8-flash-high
Google- Votes cast
- 5,076
- License type
- Closed / proprietaryProprietary
User preference score1493Based on anonymous head-to-head comparisonsLikely score range1,484.4–1,501.6View source
- Rank 10
claude-opus-5-high
Anthropic- Votes cast
- 42,617
- License type
- Closed / proprietaryProprietary
User preference score1493Based on anonymous head-to-head comparisonsLikely score range1,488.7–1,497.1View source
Showing 10 of 402
Independent sourceLMArena402 source-listed model entries · Data retrieved: Sep 19, 2026
Ranking methodEach view preserves the source’s metric, release, and methodology. Follow the links to audit the underlying work.
Ranking basis
Full published ranking and official model IDs
The main ranking preserves every publisher record and shows its source model ID or source name. Every row can be compared: exact, configuration-safe mappings use official versions; all other rows stay within one source ranking. Missing data never becomes a zero score.- 91 official model IDs
- 91
- 6 with public ranking data
- 6
- 85 awaiting comparable data
- 85
- LMArena · 402 source records retained for audit
- 402
Ranking basis
How to read this research edition
Scores stay on their original publisher scales. They are not combined into a composite score.
Missing data does not mean zero. It means the publisher did not report that metric for this snapshot.
When a source reports model settings, the position applies to that exact setup and source release—not every task, region, or deployment.
No provider can pay for placement. OpenGPT links directly to the evidence used.
Ranking basis
Data and sources
Each view preserves the source’s metric, release, and methodology. Follow the links to audit the underlying work.LiveBench
Twenty-three objective tasks across seven categories; questions refresh every six months.
- Source snapshot
- LiveBench-2026-06-25
- Data retrieved
- Oct 17, 2026
- License
- Apache-2.0 project license; exact new-livebench publication repository does not repeat a LICENSE file
Method version
A predictable publishing rhythm
OpenGPT checks active model sources every six hours. Public rankings change only through reviewed releases; paused sources remain historical.- 01
6-hour source checks
LMArena and LiveBench updates are collected and validated automatically as review candidates. Public rankings change only after the snapshot and its exact release have passed review.
- 02
Weekly change summary
Summarize meaningful ranking, model, and source changes in one reviewable update.
- 03
Monthly history snapshot
Freeze a dated snapshot with exact configurations, source releases, and corrections.