Unspecified benchmark
LM Arena Search Leaderboard
LM Arena Search is a current leaderboard that reports Arena Rating.
Updated Oct 23, 2026
Models33
Model coverage33
MetricArena Rating
EvidenceA
LM Arena Search Ranking
Higher arena rating ranks better on this benchmark.
Sort by
Rank | Model | Arena Rating | Percentile | Participants | Votes | Evidence | Evaluated |
|---|
| Rank01 | ModelOP | Arena Rating1,261.13 rating (1,254.84 rating - 1,267.42 rating) | Percentile100.00% | Participants33 | Votes60,437 | EvidenceA | Evaluated |
| Rank02 | ModelAC | Arena Rating1,261.08 rating (1,247.89 rating - 1,274.26 rating) | Percentile96.88% | Participants33 | Votes1,870 | EvidenceA | Evaluated |
| Rank03 | ModelAN | Arena Rating1,251.37 rating (1,246.83 rating - 1,255.91 rating) | Percentile93.75% | Participants33 | Votes173,191 | EvidenceA | Evaluated |
| Rank04 | ModelOP | Arena Rating1,246.55 rating (1,241.65 rating - 1,251.45 rating) | Percentile90.63% | Participants33 | Votes125,957 | EvidenceA | Evaluated |
| Rank05 | ModelAN | Arena Rating1,245.85 rating (1,238.79 rating - 1,252.90 rating) | Percentile87.50% | Participants33 | Votes12,782 | EvidenceA | Evaluated |
| Rank06 | ModelAN | Arena Rating1,241.57 rating (1,234.70 rating - 1,248.44 rating) | Percentile84.38% | Participants33 | Votes13,285 | EvidenceA | Evaluated |
| Rank07 | ModelOP | Arena Rating1,233.62 rating (1,225.77 rating - 1,241.46 rating) | Percentile81.25% | Participants33 | Votes18,483 | EvidenceA | Evaluated |
| Rank08 | ModelAN | Arena Rating1,230.15 rating (1,225.28 rating - 1,235.01 rating) | Percentile78.13% | Participants33 | Votes127,506 | EvidenceA | Evaluated |
| Rank09 | ModelAN | Arena Rating1,229.14 rating (1,222.63 rating - 1,235.65 rating) | Percentile75.00% | Participants33 | Votes73,596 | EvidenceA | Evaluated |
| Rank10 | ModelAN | Arena Rating1,220.50 rating (1,216.03 rating - 1,224.98 rating) | Percentile71.88% | Participants33 | Votes173,986 | EvidenceA | Evaluated |
| Rank11 | ModelXA | Arena Rating1,215.94 rating (1,210.08 rating - 1,221.79 rating) | Percentile68.75% | Participants33 | Votes76,458 | EvidenceA | Evaluated |
| Rank12 | ModelAN | Arena Rating1,212.75 rating (1,205.66 rating - 1,219.84 rating) | Percentile65.63% | Participants33 | Votes10,842 | EvidenceA | Evaluated |
| Rank13 | ModelGO | Arena Rating1,208.81 rating (1,204.13 rating - 1,213.48 rating) | Percentile62.50% | Participants33 | Votes151,436 | EvidenceA | Evaluated |
| Rank14 | ModelOP | Arena Rating1,207.24 rating (1,201.70 rating - 1,212.78 rating) | Percentile59.38% | Participants33 | Votes55,634 | EvidenceA | Evaluated |
| Rank15 | ModelGO | Arena Rating1,206.47 rating (1,201.00 rating - 1,211.93 rating) | Percentile56.25% | Participants33 | Votes38,857 | EvidenceA | Evaluated |
| Rank16 | ModelXA | Arena Rating1,204.80 rating (1,199.36 rating - 1,210.24 rating) | Percentile53.13% | Participants33 | Votes126,238 | EvidenceA | Evaluated |
| Rank17 | ModelAN | Arena Rating1,204.11 rating (1,198.49 rating - 1,209.73 rating) | Percentile50.00% | Participants33 | Votes106,304 | EvidenceA | Evaluated |
| Rank18 | ModelOP | Arena Rating1,199.70 rating (1,194.51 rating - 1,204.89 rating) | Percentile46.88% | Participants33 | Votes63,042 | EvidenceA | Evaluated |
| Rank19 | ModelOP | Arena Rating1,199.08 rating (1,193.60 rating - 1,204.57 rating) | Percentile43.75% | Participants33 | Votes126,730 | EvidenceA | Evaluated |
| Rank20 | ModelGO | Arena Rating1,195.69 rating (1,191.39 rating - 1,200.00 rating) | Percentile40.63% | Participants33 | Votes196,399 | EvidenceA | Evaluated |
| Rank21 | ModelAN | Arena Rating1,190.94 rating (1,184.78 rating - 1,197.10 rating) | Percentile37.50% | Participants33 | Votes72,978 | EvidenceA | Evaluated |
| Rank22 | ModelAN | Arena Rating1,179.58 rating (1,173.99 rating - 1,185.18 rating) | Percentile34.38% | Participants33 | Votes65,047 | EvidenceA | Evaluated |
| Rank23 | ModelXA | Arena Rating1,170.10 rating (1,165.47 rating - 1,174.72 rating) | Percentile31.25% | Participants33 | Votes43,083 | EvidenceA | Evaluated |
| Rank24 | ModelXA | Arena Rating1,165.81 rating (1,161.07 rating - 1,170.54 rating) | Percentile28.13% | Participants33 | Votes128,393 | EvidenceA | Evaluated |
| Rank25 | ModelAN | Arena Rating1,160.27 rating (1,155.15 rating - 1,165.39 rating) | Percentile25.00% | Participants33 | Votes144,153 | EvidenceA | Evaluated |
| Rank26 | ModelAN | Arena Rating1,148.45 rating (1,143.58 rating - 1,153.31 rating) | Percentile21.88% | Participants33 | Votes79,806 | EvidenceA | Evaluated |
| Rank27 | ModelOP | Arena Rating1,144.85 rating (1,139.25 rating - 1,150.44 rating) | Percentile18.75% | Participants33 | Votes20,770 | EvidenceA | Evaluated |
| Rank28 | ModelGO | Arena Rating1,142.80 rating (1,138.12 rating - 1,147.47 rating) | Percentile15.63% | Participants33 | Votes86,689 | EvidenceA | Evaluated |
| Rank29 | ModelXA | Arena Rating1,141.86 rating (1,135.77 rating - 1,147.95 rating) | Percentile12.50% | Participants33 | Votes19,195 | EvidenceA | Evaluated |
| Rank30 | ModelPESonar Reasoning ProPerplexity | Arena Rating1,139.01 rating (1,133.19 rating - 1,144.82 rating) | Percentile9.38% | Participants33 | Votes29,439 | EvidenceA | Evaluated |
LM Arena Search Highlights
The leading models and scores on this benchmark.
LM Arena Search Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for LM Arena Search
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is LM Arena Search?
What LM Arena Search measures and how its scores work.
LM Arena Search is a current leaderboard.
It measures Arena Rating, reported as a rating.
Scores are shown in rating. This benchmark is verified and has an evidence level of A.
- Family
- lm-arena-search
- Modality
- Unspecified
- Primary category
- Unspecified
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LM Arena. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about LM Arena Search.
Which model scores highest on LM Arena Search?
GPT-5.6 Sol is currently ranked first with 1,261.13 rating.
What are the top three models on LM Arena Search?
The current leaders are GPT-5.6 Sol (1,261.13 rating), Qwen3.8 Max (1,261.08 rating), and Claude Opus 4.6 (1,251.37 rating).
Which LM Arena Search model has the lowest official input price?
Gemini 3 Flash has the lowest matched official input price at $0.50 input / $3.0 output per 1M tokens.
Which models are fastest among LM Arena Search results?
The fastest matched records are GPT-5.2 (100.00 tok/s via OpenAI), GPT-5.1 (100.00 tok/s via OpenAI), and Claude Opus 4.1 (100.00 tok/s via Anthropic).
Does the highest arena rating result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.