Unspecified benchmark
LM Arena Vision Leaderboard
LM Arena Vision is a current leaderboard.
Updated Oct 23, 2026
Models100
Model coverage113
MetricArena Rating
EvidenceA
LM Arena Vision Ranking
Higher arena rating ranks better on this benchmark.
Sort by
Rank | Model | Arena Rating | Percentile | Participants | Votes | Evidence | Evaluated |
|---|
| Rank01 | ModelAN | Arena Rating1,324.88 rating (1,317.85 rating - 1,331.91 rating) | Percentile100.00% | Participants113 | Votes14,714 | EvidenceA | Evaluated |
| Rank02 | ModelAN | Arena Rating1,320.82 rating (1,309.11 rating - 1,332.54 rating) | Percentile99.11% | Participants113 | Votes3,035 | EvidenceA | Evaluated |
| Rank03 | ModelAN | Arena Rating1,319.62 rating (1,313.01 rating - 1,326.23 rating) | Percentile98.21% | Participants113 | Votes17,743 | EvidenceA | Evaluated |
| Rank04 | ModelAN | Arena Rating1,319.49 rating (1,310.21 rating - 1,328.77 rating) | Percentile97.32% | Participants113 | Votes5,026 | EvidenceA | Evaluated |
| Rank05 | ModelAN | Arena Rating1,316.94 rating (1,310.39 rating - 1,323.49 rating) | Percentile96.43% | Participants113 | Votes23,139 | EvidenceA | Evaluated |
| Rank06 | ModelAN | Arena Rating1,315.67 rating (1,309.30 rating - 1,322.05 rating) | Percentile95.54% | Participants113 | Votes22,286 | EvidenceA | Evaluated |
| Rank07 | ModelGO | Arena Rating1,315.38 rating (1,305.64 rating - 1,325.12 rating) | Percentile94.64% | Participants113 | Votes4,645 | EvidenceA | Evaluated |
| Rank08 | ModelGO | Arena Rating1,314.23 rating (1,305.05 rating - 1,323.40 rating) | Percentile93.75% | Participants113 | Votes5,369 | EvidenceA | Evaluated |
| Rank09 | ModelAC | Arena Rating1,312.94 rating (1,305.49 rating - 1,320.38 rating) | Percentile92.86% | Participants113 | Votes9,957 | EvidenceA | Evaluated |
| Rank10 | ModelME | Arena Rating1,308.41 rating (1,299.26 rating - 1,317.57 rating) | Percentile91.96% | Participants113 | Votes5,392 | EvidenceA | Evaluated |
| Rank11 | ModelGO | Arena Rating1,308.33 rating (1,301.51 rating - 1,315.14 rating) | Percentile91.07% | Participants113 | Votes13,862 | EvidenceA | Evaluated |
| Rank12 | ModelME | Arena Rating1,305.77 rating (1,296.70 rating - 1,314.85 rating) | Percentile90.18% | Participants113 | Votes5,865 | EvidenceA | Evaluated |
| Rank13 | ModelGO | Arena Rating1,304.75 rating (1,297.39 rating - 1,312.12 rating) | Percentile89.29% | Participants113 | Votes13,623 | EvidenceA | Evaluated |
| Rank14 | ModelME | Arena Rating1,304.22 rating (1,289.89 rating - 1,318.54 rating) | Percentile88.39% | Participants113 | Votes1,948 | EvidenceA | Evaluated |
| Rank15 | ModelOP | Arena Rating1,302.63 rating (1,296.94 rating - 1,308.32 rating) | Percentile87.50% | Participants113 | Votes30,747 | EvidenceA | Evaluated |
| Rank16 | ModelGO | Arena Rating1,298.88 rating (1,291.01 rating - 1,306.75 rating) | Percentile86.61% | Participants113 | Votes8,979 | EvidenceA | Evaluated |
| Rank17 | ModelOP | Arena Rating1,297.00 rating (1,291.24 rating - 1,302.75 rating) | Percentile85.71% | Participants113 | Votes28,781 | EvidenceA | Evaluated |
| Rank18 | ModelGO | Arena Rating1,295.78 rating (1,290.67 rating - 1,300.89 rating) | Percentile84.82% | Participants113 | Votes47,114 | EvidenceA | Evaluated |
| Rank19 | ModelAN | Arena Rating1,294.49 rating (1,288.04 rating - 1,300.94 rating) | Percentile83.93% | Participants113 | Votes18,303 | EvidenceA | Evaluated |
| Rank20 | ModelZA | Arena Rating1,293.87 rating (1,287.50 rating - 1,300.23 rating) | Percentile83.04% | Participants113 | Votes16,254 | EvidenceA | Evaluated |
| Rank21 | ModelME | Arena Rating1,292.50 rating (1,285.61 rating - 1,299.40 rating) | Percentile82.14% | Participants113 | Votes12,804 | EvidenceA | Evaluated |
| Rank22 | ModelAN | Arena Rating1,287.22 rating (1,274.71 rating - 1,299.73 rating) | Percentile81.25% | Participants113 | Votes2,564 | EvidenceA | Evaluated |
| Rank23 | ModelXA | Arena Rating1,287.12 rating (1,280.07 rating - 1,294.17 rating) | Percentile80.36% | Participants113 | Votes12,599 | EvidenceA | Evaluated |
| Rank24 | ModelGO | Arena Rating1,284.95 rating (1,279.76 rating - 1,290.14 rating) | Percentile79.46% | Participants113 | Votes39,131 | EvidenceA | Evaluated |
| Rank25 | ModelAN | Arena Rating1,282.76 rating (1,276.66 rating - 1,288.87 rating) | Percentile78.57% | Participants113 | Votes27,408 | EvidenceA | Evaluated |
| Rank26 | ModelMA | Arena Rating1,282.11 rating (1,275.34 rating - 1,288.88 rating) | Percentile77.68% | Participants113 | Votes16,368 | EvidenceA | Evaluated |
| Rank27 | ModelOP | Arena Rating1,280.62 rating (1,273.33 rating - 1,287.91 rating) | Percentile76.79% | Participants113 | Votes11,439 | EvidenceA | Evaluated |
| Rank28 | ModelOP | Arena Rating1,279.90 rating (1,269.63 rating - 1,290.17 rating) | Percentile75.89% | Participants113 | Votes4,012 | EvidenceA | Evaluated |
| Rank29 | ModelAC | Arena Rating1,278.15 rating (1,271.47 rating - 1,284.82 rating) | Percentile75.00% | Participants113 | Votes14,212 | EvidenceA | Evaluated |
| Rank30 | ModelGO | Arena Rating1,276.47 rating (1,270.80 rating - 1,282.14 rating) | Percentile74.11% | Participants113 | Votes40,219 | EvidenceA | Evaluated |
LM Arena Vision Highlights
The leading models and scores on this benchmark.
LM Arena Vision Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for LM Arena Vision
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 Vision?
What LM Arena Vision measures and how its scores work.
LM Arena Vision is a benchmark leaderboard.
It reports Arena Rating, with the unit listed as rating.
Scores are shown in rating. This benchmark is verified and has an evidence level of A.
- Family
- lm-arena-vision
- 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 Vision.
Which model scores highest on LM Arena Vision?
Claude Fable 5 is currently ranked first with 1,324.88 rating.
What are the top three models on LM Arena Vision?
The current leaders are Claude Fable 5 (1,324.88 rating), Claude Opus 5.5 (1,320.82 rating), and Claude Opus 5 (1,319.62 rating).
Which LM Arena Vision model has the lowest official input price?
GPT-5 nano has the lowest matched official input price at $0.05 input / $0.40 output per 1M tokens.
Which models are fastest among LM Arena Vision results?
The fastest matched records are Llama 4 Scout (776.10 tok/s via Groq), Llama 4 Maverick (638.70 tok/s via Sambanova), and GPT-5 nano (500.00 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.