Benchmark
LMArena Text Leaderboard
People compare model answers and choose which they prefer.
All human preference benchmarksScores from LLM Stats data.
- Models measured
- 1
- Scores recorded
- 2
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 1,474
- Mean
- 1,483
- Median
- 9
- Std dev
- 1,465
- 10th percentile
- 1,483
- 90th percentile
- 1,465
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Grok 4.1thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 1,483 |
| 2 | Grok 4.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 1,465 |
Data credits: Data by LLM Stats