Unspecified benchmark
LM Arena Search Style Control Leaderboard
LM Arena Search Style Control is a current leaderboard using the Arena Rating metric.
Updated Oct 23, 2026
Models33
Model coverage33
MetricArena Rating
EvidenceA
LM Arena Search Style Control Ranking
Higher arena rating ranks better on this benchmark.
Sort by
Rank | Model | Arena Rating | Percentile | Participants | Votes | Evidence | Evaluated |
|---|
| Rank01 | ModelOP | Arena Rating1,257.93 rating (1,251.46 rating - 1,264.40 rating) | Percentile100.00% | Participants33 | Votes60,437 | EvidenceA | Evaluated |
| Rank02 | ModelOP | Arena Rating1,246.24 rating (1,238.20 rating - 1,254.28 rating) | Percentile96.88% | Participants33 | Votes18,483 | EvidenceA | Evaluated |
| Rank03 | ModelAN | Arena Rating1,233.37 rating (1,226.20 rating - 1,240.54 rating) | Percentile93.75% | Participants33 | Votes12,782 | EvidenceA | Evaluated |
| Rank04 | ModelAC | Arena Rating1,229.50 rating (1,216.20 rating - 1,242.79 rating) | Percentile90.63% | Participants33 | Votes1,870 | EvidenceA | Evaluated |
| Rank05 | ModelAN | Arena Rating1,229.02 rating (1,222.44 rating - 1,235.60 rating) | Percentile87.50% | Participants33 | Votes73,596 | EvidenceA | Evaluated |
| Rank06 | ModelOP | Arena Rating1,226.45 rating (1,221.46 rating - 1,231.45 rating) | Percentile84.38% | Participants33 | Votes125,957 | EvidenceA | Evaluated |
| Rank07 | ModelAN | Arena Rating1,222.05 rating (1,217.36 rating - 1,226.73 rating) | Percentile81.25% | Participants33 | Votes173,191 | EvidenceA | Evaluated |
| Rank08 | ModelAN | Arena Rating1,214.35 rating (1,207.46 rating - 1,221.24 rating) | Percentile78.13% | Participants33 | Votes13,285 | EvidenceA | Evaluated |
| Rank09 | ModelAN | Arena Rating1,211.23 rating (1,204.13 rating - 1,218.32 rating) | Percentile75.00% | Participants33 | Votes10,842 | EvidenceA | Evaluated |
| Rank10 | ModelAN | Arena Rating1,209.71 rating (1,204.77 rating - 1,214.64 rating) | Percentile71.88% | Participants33 | Votes127,506 | EvidenceA | Evaluated |
| Rank11 | ModelGO | Arena Rating1,206.62 rating (1,201.83 rating - 1,211.40 rating) | Percentile68.75% | Participants33 | Votes151,436 | EvidenceA | Evaluated |
| Rank12 | ModelXA | Arena Rating1,206.38 rating (1,200.83 rating - 1,211.94 rating) | Percentile65.63% | Participants33 | Votes126,238 | EvidenceA | Evaluated |
| Rank13 | ModelXA | Arena Rating1,206.19 rating (1,200.29 rating - 1,212.09 rating) | Percentile62.50% | Participants33 | Votes76,458 | EvidenceA | Evaluated |
| Rank14 | ModelAN | Arena Rating1,201.93 rating (1,197.26 rating - 1,206.60 rating) | Percentile59.38% | Participants33 | Votes173,986 | EvidenceA | Evaluated |
| Rank15 | ModelGO | Arena Rating1,200.75 rating (1,195.26 rating - 1,206.24 rating) | Percentile56.25% | Participants33 | Votes38,857 | EvidenceA | Evaluated |
| Rank16 | ModelOP | Arena Rating1,196.26 rating (1,190.59 rating - 1,201.94 rating) | Percentile53.13% | Participants33 | Votes126,730 | EvidenceA | Evaluated |
| Rank17 | ModelOP | Arena Rating1,196.16 rating (1,189.43 rating - 1,202.90 rating) | Percentile50.00% | Participants33 | Votes20,770 | EvidenceA | Evaluated |
| Rank18 | ModelAN | Arena Rating1,195.25 rating (1,189.61 rating - 1,200.89 rating) | Percentile46.88% | Participants33 | Votes106,304 | EvidenceA | Evaluated |
| Rank19 | ModelAN | Arena Rating1,193.16 rating (1,186.87 rating - 1,199.45 rating) | Percentile43.75% | Participants33 | Votes72,978 | EvidenceA | Evaluated |
| Rank20 | ModelXA | Arena Rating1,192.79 rating (1,187.93 rating - 1,197.65 rating) | Percentile40.63% | Participants33 | Votes128,393 | EvidenceA | Evaluated |
| Rank21 | ModelGO | Arena Rating1,188.68 rating (1,184.28 rating - 1,193.07 rating) | Percentile37.50% | Participants33 | Votes196,399 | EvidenceA | Evaluated |
| Rank22 | ModelOP | Arena Rating1,187.73 rating (1,180.35 rating - 1,195.11 rating) | Percentile34.38% | Participants33 | Votes20,865 | EvidenceA | Evaluated |
| Rank23 | ModelAN | Arena Rating1,186.69 rating (1,180.96 rating - 1,192.42 rating) | Percentile31.25% | Participants33 | Votes65,047 | EvidenceA | Evaluated |
| Rank24 | ModelOP | Arena Rating1,183.64 rating (1,178.27 rating - 1,189.02 rating) | Percentile28.13% | Participants33 | Votes63,042 | EvidenceA | Evaluated |
| Rank25 | ModelAN | Arena Rating1,175.98 rating (1,170.74 rating - 1,181.21 rating) | Percentile25.00% | Participants33 | Votes144,153 | EvidenceA | Evaluated |
| Rank26 | ModelAN | Arena Rating1,167.09 rating (1,162.11 rating - 1,172.07 rating) | Percentile21.88% | Participants33 | Votes79,806 | EvidenceA | Evaluated |
| Rank27 | ModelOP | Arena Rating1,161.40 rating (1,155.60 rating - 1,167.20 rating) | Percentile18.75% | Participants33 | Votes55,634 | EvidenceA | Evaluated |
| Rank28 | ModelXA | Arena Rating1,161.08 rating (1,156.26 rating - 1,165.89 rating) | Percentile15.63% | Participants33 | Votes43,083 | EvidenceA | Evaluated |
| Rank29 | ModelAN | Arena Rating1,151.84 rating (1,146.29 rating - 1,157.39 rating) | Percentile12.50% | Participants33 | Votes31,506 | EvidenceA | Evaluated |
| Rank30 | ModelGO | Arena Rating1,144.23 rating (1,139.43 rating - 1,149.03 rating) | Percentile9.38% | Participants33 | Votes86,689 | EvidenceA | Evaluated |
LM Arena Search Style Control Highlights
The leading models and scores on this benchmark.
LM Arena Search Style Control Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for LM Arena Search Style Control
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 Style Control?
What LM Arena Search Style Control measures and how its scores work.
LM Arena Search Style Control is a current leaderboard.
It measures Arena Rating, reported in rating units.
Scores are shown in rating. This benchmark is verified and has an evidence level of A.
- Family
- lm-arena-search-style-control
- 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 Style Control.
Which model scores highest on LM Arena Search Style Control?
GPT-5.6 Sol is currently ranked first with 1,257.93 rating.
What are the top three models on LM Arena Search Style Control?
The current leaders are GPT-5.6 Sol (1,257.93 rating), GPT-6 Astra (1,246.24 rating), and Claude Fable 5.1 (1,233.37 rating).
Which LM Arena Search Style Control 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 Style Control results?
The fastest matched records are GPT-5 (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.