Unspecified benchmark
LM Arena Text Factuality Leaderboard
LM Arena Text Factuality is a benchmark with a current leaderboard using Arena Rating.
Updated Oct 23, 2026
Models100
Model coverage131
MetricArena Rating
EvidenceA
LM Arena Text Factuality Ranking
Higher arena rating ranks better on this benchmark.
Sort by
Rank | Model | Arena Rating | Percentile | Participants | Votes | Evidence | Evaluated |
|---|
| Rank01 | ModelGO | Arena Rating1,511.16 rating (1,503.71 rating - 1,518.62 rating) | Percentile100.00% | Participants131 | Votes4,900 | EvidenceA | Evaluated |
| Rank02 | ModelAN | Arena Rating1,508.86 rating (1,502.84 rating - 1,514.88 rating) | Percentile99.23% | Participants131 | Votes9,496 | EvidenceA | Evaluated |
| Rank03 | ModelAN | Arena Rating1,498.08 rating (1,493.03 rating - 1,503.13 rating) | Percentile98.46% | Participants131 | Votes15,623 | EvidenceA | Evaluated |
| Rank04 | ModelAN | Arena Rating1,492.49 rating (1,489.83 rating - 1,495.15 rating) | Percentile97.69% | Participants131 | Votes82,290 | EvidenceA | Evaluated |
| Rank05 | ModelAN | Arena Rating1,489.15 rating (1,485.31 rating - 1,492.98 rating) | Percentile96.92% | Participants131 | Votes33,683 | EvidenceA | Evaluated |
| Rank06 | ModelOP | Arena Rating1,485.68 rating (1,482.83 rating - 1,488.54 rating) | Percentile96.15% | Participants131 | Votes69,294 | EvidenceA | Evaluated |
| Rank07 | ModelOP | Arena Rating1,484.41 rating (1,481.47 rating - 1,487.36 rating) | Percentile95.38% | Participants131 | Votes64,669 | EvidenceA | Evaluated |
| Rank08 | ModelXI | Arena Rating1,483.94 rating (1,475.98 rating - 1,491.89 rating) | Percentile94.62% | Participants131 | Votes4,065 | EvidenceA | Evaluated |
| Rank09 | ModelAN | Arena Rating1,483.19 rating (1,479.83 rating - 1,486.55 rating) | Percentile93.85% | Participants131 | Votes43,399 | EvidenceA | Evaluated |
| Rank10 | ModelGO | Arena Rating1,481.27 rating (1,477.86 rating - 1,484.68 rating) | Percentile93.08% | Participants131 | Votes41,125 | EvidenceA | Evaluated |
| Rank11 | ModelAC | Arena Rating1,479.79 rating (1,471.03 rating - 1,488.55 rating) | Percentile92.31% | Participants131 | Votes3,942 | EvidenceA | Evaluated |
| Rank12 | ModelME | Arena Rating1,479.34 rating (1,474.65 rating - 1,484.03 rating) | Percentile91.54% | Participants131 | Votes19,323 | EvidenceA | Evaluated |
| Rank13 | ModelME | Arena Rating1,479.32 rating (1,473.44 rating - 1,485.19 rating) | Percentile90.77% | Participants131 | Votes9,578 | EvidenceA | Evaluated |
| Rank14 | ModelAN | Arena Rating1,477.31 rating (1,474.29 rating - 1,480.32 rating) | Percentile90.00% | Participants131 | Votes65,036 | EvidenceA | Evaluated |
| Rank15 | ModelAN | Arena Rating1,477.00 rating (1,470.78 rating - 1,483.22 rating) | Percentile89.23% | Participants131 | Votes8,126 | EvidenceA | Evaluated |
| Rank16 | ModelGO | Arena Rating1,476.92 rating (1,473.60 rating - 1,480.24 rating) | Percentile88.46% | Participants131 | Votes48,479 | EvidenceA | Evaluated |
| Rank17 | ModelGO | Arena Rating1,476.02 rating (1,472.05 rating - 1,479.99 rating) | Percentile87.69% | Participants131 | Votes29,177 | EvidenceA | Evaluated |
| Rank18 | ModelOP | Arena Rating1,475.89 rating (1,472.51 rating - 1,479.26 rating) | Percentile86.92% | Participants131 | Votes41,803 | EvidenceA | Evaluated |
| Rank19 | ModelGO | Arena Rating1,473.29 rating (1,469.43 rating - 1,477.15 rating) | Percentile86.15% | Participants131 | Votes41,423 | EvidenceA | Evaluated |
| Rank20 | ModelMA | Arena Rating1,471.92 rating (1,468.34 rating - 1,475.49 rating) | Percentile85.38% | Participants131 | Votes34,325 | EvidenceA | Evaluated |
| Rank21 | ModelAC | Arena Rating1,471.91 rating (1,467.81 rating - 1,476.01 rating) | Percentile84.62% | Participants131 | Votes29,418 | EvidenceA | Evaluated |
| Rank22 | ModelGO | Arena Rating1,471.75 rating (1,469.47 rating - 1,474.04 rating) | Percentile83.85% | Participants131 | Votes129,183 | EvidenceA | Evaluated |
| Rank23 | ModelGO | Arena Rating1,471.68 rating (1,468.05 rating - 1,475.30 rating) | Percentile83.08% | Participants131 | Votes36,079 | EvidenceA | Evaluated |
| Rank24 | ModelAN | Arena Rating1,469.63 rating (1,466.54 rating - 1,472.71 rating) | Percentile82.31% | Participants131 | Votes64,008 | EvidenceA | Evaluated |
| Rank25 | ModelOP | Arena Rating1,467.99 rating (1,464.73 rating - 1,471.25 rating) | Percentile81.54% | Participants131 | Votes45,201 | EvidenceA | Evaluated |
| Rank26 | ModelME | Arena Rating1,467.64 rating (1,462.20 rating - 1,473.09 rating) | Percentile80.77% | Participants131 | Votes14,135 | EvidenceA | Evaluated |
| Rank27 | ModelGO | Arena Rating1,467.48 rating (1,463.54 rating - 1,471.43 rating) | Percentile80.00% | Participants131 | Votes30,662 | EvidenceA | Evaluated |
| Rank28 | ModelZA | Arena Rating1,466.98 rating (1,462.66 rating - 1,471.30 rating) | Percentile79.23% | Participants131 | Votes24,035 | EvidenceA | Evaluated |
| Rank29 | ModelOP | Arena Rating1,465.78 rating (1,460.58 rating - 1,470.98 rating) | Percentile78.46% | Participants131 | Votes13,293 | EvidenceA | Evaluated |
| Rank30 | ModelXA | Arena Rating1,465.31 rating (1,461.86 rating - 1,468.75 rating) | Percentile77.69% | Participants131 | Votes39,844 | EvidenceA | Evaluated |
LM Arena Text Factuality Highlights
The leading models and scores on this benchmark.
LM Arena Text Factuality Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for LM Arena Text Factuality
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 Factuality?
What LM Arena Text Factuality measures and how its scores work.
LM Arena Text Factuality is a benchmark for text factuality.
It reports Arena Rating in rating units.
Scores are shown in rating. This benchmark is verified and has an evidence level of A.
- Family
- lm-arena-text-factuality
- 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 Factuality.
Which model scores highest on LM Arena Text Factuality?
Gemini 4 Argon is currently ranked first with 1,511.16 rating.
What are the top three models on LM Arena Text Factuality?
The current leaders are Gemini 4 Argon (1,511.16 rating), Claude Opus 5.5 (1,508.86 rating), and Claude Fable 5.1 (1,498.08 rating).
Which LM Arena Text Factuality model has the lowest official input price?
GLM-5.3-Flash has the lowest matched official input price at $0.12 input / $0.42 output per 1M tokens.
Which models are fastest among LM Arena Text Factuality results?
The fastest matched records are Gemini 3.7 Flash (409.96 tok/s via Google), GPT-5.6 Luna (215.52 tok/s via OpenAI), and ChatGPT-4o Latest (132.00 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.