reasoning benchmark
LMArena Text Leaderboard
LMArena Text Leaderboard is a blind human preference evaluation benchmark that ranks models based on pairwise comparisons in real-world conversations. The leaderboard uses Elo ratings computed from user preferences in head-to-head model battles, providing a comprehensive measure of overall model capability and style.
Updated Aug 11, 2026
Models2
Model coverage2
MetricScore
EvidenceB
LMArena Text Leaderboard Ranking
Higher score ranks better on this benchmark.
| 1 | XA | 1,483 points | 100.0% | 2 | C | |
| 2 | XA | 1,465 points | 0.0% | 2 | C |
LMArena Text Leaderboard Score Distribution
A closer view of the leading scores on this benchmark.
LMArena Text Leaderboard Highlights
The leading models and scores on this benchmark.
What is LMArena Text Leaderboard?
What LMArena Text Leaderboard measures and how its scores work.
LMArena Text Leaderboard is a blind human preference evaluation benchmark that ranks models based on pairwise comparisons in real-world conversations. The leaderboard uses Elo ratings computed from user preferences in head-to-head model battles, providing a comprehensive measure of overall model capability and style.
Scores are shown in points. This benchmark is not independently verified and has an evidence level of B.
- Family
- LMArena Text Leaderboard
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- lmarena-text|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about LMArena Text Leaderboard.
Which model scores highest on LMArena Text Leaderboard?
Grok-4.1 Thinking is currently ranked first with 1,483 points.
What does LMArena Text Leaderboard measure?
LMArena Text Leaderboard is a blind human preference evaluation benchmark that ranks models based on pairwise comparisons in real-world conversations. The leaderboard uses Elo ratings computed from user preferences in head-to-head model battles, providing a comprehensive measure of overall model capability and style.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.