Unspecified benchmark
LM Arena Text Style Control Leaderboard
LM Arena Text Style Control is listed with an Arena Rating measured in rating units.
Updated Sep 8, 2026
Models100
Model coverage210
MetricArena Rating
EvidenceA
LM Arena Text Style Control Ranking
Higher arena rating ranks better on this benchmark.
Sort by
Rank | Model | Arena Rating | Percentile | Participants | Votes | Evidence | Evaluated |
|---|
| Rank01 | ModelAN | Arena Rating1,507.16 rating (1,502.20 rating - 1,512.13 rating) | Percentile100.00% | Participants210 | Votes27,189 | EvidenceA | Evaluated |
| Rank02 | ModelAN | Arena Rating1,504.84 rating (1,501.32 rating - 1,508.36 rating) | Percentile99.52% | Participants210 | Votes72,099 | EvidenceA | Evaluated |
| Rank03 | ModelAN | Arena Rating1,504.21 rating (1,493.02 rating - 1,515.41 rating) | Percentile99.04% | Participants210 | Votes2,906 | EvidenceA | Evaluated |
| Rank04 | ModelAN | Arena Rating1,502.11 rating (1,498.22 rating - 1,505.99 rating) | Percentile98.56% | Participants210 | Votes60,103 | EvidenceA | Evaluated |
| Rank05 | ModelME | Arena Rating1,498.99 rating (1,488.50 rating - 1,509.48 rating) | Percentile98.09% | Participants210 | Votes3,240 | EvidenceA | Evaluated |
| Rank06 | ModelGO | Arena Rating1,493.85 rating (1,485.29 rating - 1,502.40 rating) | Percentile97.61% | Participants210 | Votes5,125 | EvidenceA | Evaluated |
| Rank07 | ModelAN | Arena Rating1,493.33 rating (1,488.76 rating - 1,497.89 rating) | Percentile97.13% | Participants210 | Votes35,174 | EvidenceA | Evaluated |
| Rank08 | ModelME | Arena Rating1,492.06 rating (1,487.02 rating - 1,497.10 rating) | Percentile96.65% | Participants210 | Votes24,064 | EvidenceA | Evaluated |
| Rank09 | ModelGO | Arena Rating1,490.93 rating (1,482.75 rating - 1,499.10 rating) | Percentile96.17% | Participants210 | Votes5,682 | EvidenceA | Evaluated |
| Rank10 | ModelMA | Arena Rating1,488.67 rating (1,483.21 rating - 1,494.13 rating) | Percentile95.69% | Participants210 | Votes18,090 | EvidenceA | Evaluated |
| Rank11 | ModelME | Arena Rating1,488.17 rating (1,482.32 rating - 1,494.01 rating) | Percentile95.22% | Participants210 | Votes13,572 | EvidenceA | Evaluated |
| Rank12 | ModelGO | Arena Rating1,486.73 rating (1,483.52 rating - 1,489.94 rating) | Percentile94.74% | Participants210 | Votes102,999 | EvidenceA | Evaluated |
| Rank13 | ModelGO | Arena Rating1,485.58 rating (1,481.72 rating - 1,489.43 rating) | Percentile94.26% | Participants210 | Votes40,668 | EvidenceA | Evaluated |
| Rank14 | ModelOP | Arena Rating1,483.15 rating (1,478.04 rating - 1,488.26 rating) | Percentile93.78% | Participants210 | Votes23,413 | EvidenceA | Evaluated |
| Rank15 | ModelAN | Arena Rating1,482.31 rating (1,478.06 rating - 1,486.57 rating) | Percentile93.30% | Participants210 | Votes48,727 | EvidenceA | Evaluated |
| Rank16 | ModelOP | Arena Rating1,482.09 rating (1,478.24 rating - 1,485.93 rating) | Percentile92.82% | Participants210 | Votes63,547 | EvidenceA | Evaluated |
| Rank17 | ModelZA | Arena Rating1,482.04 rating (1,474.74 rating - 1,489.34 rating) | Percentile92.34% | Participants210 | Votes7,668 | EvidenceA | Evaluated |
| Rank18 | ModelGO | Arena Rating1,480.20 rating (1,475.08 rating - 1,485.31 rating) | Percentile91.87% | Participants210 | Votes22,286 | EvidenceA | Evaluated |
| Rank19 | ModelAC | Arena Rating1,479.56 rating (1,473.34 rating - 1,485.78 rating) | Percentile91.39% | Participants210 | Votes13,346 | EvidenceA | Evaluated |
| Rank20 | ModelGO | Arena Rating1,479.43 rating (1,475.10 rating - 1,483.77 rating) | Percentile90.91% | Participants210 | Votes34,180 | EvidenceA | Evaluated |
| Rank21 | ModelOP | Arena Rating1,476.55 rating (1,472.67 rating - 1,480.43 rating) | Percentile90.43% | Participants210 | Votes60,624 | EvidenceA | Evaluated |
| Rank22 | ModelOP | Arena Rating1,476.29 rating (1,472.16 rating - 1,480.43 rating) | Percentile89.95% | Participants210 | Votes34,217 | EvidenceA | Evaluated |
| Rank23 | ModelZA | Arena Rating1,474.16 rating (1,465.24 rating - 1,483.08 rating) | Percentile89.47% | Participants210 | Votes4,672 | EvidenceA | Evaluated |
| Rank24 | ModelGO | Arena Rating1,473.83 rating (1,469.41 rating - 1,478.25 rating) | Percentile89.00% | Participants210 | Votes30,244 | EvidenceA | Evaluated |
| Rank25 | ModelOP | Arena Rating1,473.71 rating (1,468.60 rating - 1,478.83 rating) | Percentile88.52% | Participants210 | Votes25,860 | EvidenceA | Evaluated |
| Rank26 | ModelAC | Arena Rating1,473.62 rating (1,463.62 rating - 1,483.62 rating) | Percentile88.04% | Participants210 | Votes3,710 | EvidenceA | Evaluated |
| Rank27 | ModelAN | Arena Rating1,472.84 rating (1,468.93 rating - 1,476.74 rating) | Percentile87.56% | Participants210 | Votes36,269 | EvidenceA | Evaluated |
| Rank28 | ModelAN | Arena Rating1,472.39 rating (1,468.78 rating - 1,476.00 rating) | Percentile87.08% | Participants210 | Votes66,316 | EvidenceA | Evaluated |
| Rank29 | ModelXA | Arena Rating1,471.72 rating (1,467.94 rating - 1,475.50 rating) | Percentile86.60% | Participants210 | Votes62,251 | EvidenceA | Evaluated |
| Rank30 | ModelZA | Arena Rating1,471.72 rating (1,467.00 rating - 1,476.43 rating) | Percentile86.12% | Participants210 | Votes33,966 | EvidenceA | Evaluated |
LM Arena Text Style Control Highlights
The leading models and scores on this benchmark.
LM Arena Text Style Control Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for LM Arena Text 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 Text Style Control?
What LM Arena Text Style Control measures and how its scores work.
LM Arena Text Style Control is a benchmark with 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-text-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 Text Style Control.
Which model scores highest on LM Arena Text Style Control?
Claude Fable 5 is currently ranked first with 1,507.16 rating.
What are the top three models on LM Arena Text Style Control?
The current leaders are Claude Fable 5 (1,507.16 rating), Claude Opus 4.6 (1,504.84 rating), and Claude Fable 5.1 (1,504.21 rating).
Which LM Arena Text Style Control model has the lowest official input price?
GLM-5.3-Flash has the lowest matched official input price at $0.08 input / $0.25 output per 1M tokens.
Which models are fastest among LM Arena Text Style Control results?
The fastest matched records are GLM-5.3 (472.69 tok/s via FriendliAI), Gemini 3.5 Flash (210.94 tok/s via Google), and GPT-5.5 Instant (206.89 tok/s via OpenAI).
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.